© 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. 4765
    Prev
    Next
    INDEX
    Explanations

    personal pronouns or titles which refer to a person

    oai_token-act-pair · gemini-2.0-flash

    say "modal verb"

    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
     be
    -0.68
     been
    -0.67
     come
    -0.60
     use
    -0.56
     take
    -0.56
    M
    -0.53
     follow
    -0.52
    be
    -0.52
     going
    -0.50
    ское
    -0.50
    POSITIVE LOGITS
    tagHelperRunner
    1.21
    Билгалдахарш
    1.01
     للاسماء
    1.00
    ValueStyle
    0.98
    OGND
    0.96
     समीक्षक
    0.95
     myſelf
    0.93
     ComVisible
    0.91
     betweenstory
    0.91
     дописавши
    0.91
    Activations Density 0.813%

    No Known Activations