© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3142
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and associated words or phrases

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    EndInit
    -0.93
    DockStyle
    -0.90
    CloseOperation
    -0.86
    BrowserModule
    -0.83
     صوتيه
    -0.81
     GoogleFonts
    -0.81
     ExecuteAsync
    -0.80
     estekak
    -0.80
     nahilalakip
    -0.79
     Drapeau
    -0.79
    POSITIVE LOGITS
     heard
    0.47
     hear
    0.44
     Read
    0.41
    Read
    0.41
    Full
    0.39
     bevis
    0.39
    {~
    0.39
     nej
    0.39
    Urls
    0.38
    咽
    0.38
    Activations Density 0.773%

    No Known Activations