© 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. 9492
    Prev
    Next
    INDEX
    Explanations

    uses of the verb "to be" and pronouns

    oai_token-act-pair · gemini-2.0-flash

    terms related to discovery

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

    find

    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
    PageRoute
    -0.60
     AspNetCore
    -0.57
    StoryboardSegue
    -0.56
    verwijspagina
    -0.54
    ContentAsync
    -0.52
    NameInMap
    -0.52
    MLLoader
    -0.50
    istoitu
    -0.49
    ISupport
    -0.49
    données
    -0.49
    POSITIVE LOGITS
     found
    2.52
     find
    2.34
     finding
    2.23
    found
    2.20
    find
    2.20
     finds
    2.19
     Found
    2.09
     FIND
    2.05
     Find
    2.05
    Find
    2.03
    Activations Density 3.431%

    No Known Activations