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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15097
    Prev
    Next
    INDEX
    Explanations

    words related to advice and suggestions, typically incorporating "you", "will" and modal verbs.

    oai_token-act-pair · gemini-2.0-flash

    blog posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     uș
    -0.50
    namon
    -0.47
    Dragged
    -0.46
     Attila
    -0.45
     GenerationType
    -0.44
    Bioaccumulative
    -0.44
    Interim
    -0.44
    SceneManagement
    -0.43
     Interim
    -0.43
     Gegenstand
    -0.43
    POSITIVE LOGITS
    Rhestr
    0.68
    EndInit
    0.64
    geme
    0.64
    AnchorStyles
    0.60
     estekak
    0.59
    بوابة
    0.56
    הערות
    0.55
    writeFieldEnd
    0.55
    BeginInit
    0.53
     numberWith
    0.52
    Activations Density 0.589%

    No Known Activations