© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7462
    Prev
    Next
    INDEX
    Explanations

    a hodgepodge of words, including article prepositions conjunctions, but seems to focus more on ones that describe location, reasoning, or argumentation

    oai_token-act-pair · gemini-2.0-flash

    references to 'people'

    np_token-act-pair-logits · gpt-4o-mini

    people

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Infórmanos
    -0.60
    richTextPanel
    -0.59
    AddHtmlAttribute
    -0.59
     समीक्षाओं
    -0.59
    StructEnd
    -0.59
    DrawerToggle
    -0.59
    IsContent
    -0.58
    évaluateur
    -0.57
     tartalomajánló
    -0.56
    WebVitals
    -0.53
    POSITIVE LOGITS
     people
    3.11
    people
    2.81
    People
    2.48
     persons
    2.36
     People
    2.34
     PEOPLE
    2.30
     person
    2.23
    PEOPLE
    2.09
     pessoas
    2.03
     personnes
    2.02
    Activations Density 2.103%

    No Known Activations