© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5972
    Prev
    Next
    INDEX
    Explanations

    phrases about physical violence or discipline

    oai_token-act-pair · gemini-2.0-flash

    violent actions

    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
    denza
    -0.43
    risa
    -0.43
    ic
    -0.43
    addOn
    -0.42
    raction
    -0.42
    rm
    -0.41
     terk
    -0.41
    cis
    -0.41
    ché
    -0.40
     echi
    -0.40
    POSITIVE LOGITS
    IBarButtonItem
    1.02
    UserScript
    0.80
     kick
    0.78
     punch
    0.77
     slap
    0.71
    initComponents
    0.71
     blow
    0.68
     slaps
    0.65
     KICK
    0.64
    VIAF
    0.63
    Activations Density 0.933%

    No Known Activations