© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14317
    Prev
    Next
    INDEX
    Explanations

    violent news events like attacks and killing

    oai_token-act-pair · gemini-2.0-flash

    kill

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     roupa
    -0.51
     Liturgy
    -0.47
     roupas
    -0.47
     chapéu
    -0.46
    Catégorie
    -0.45
     näky
    -0.45
     povin
    -0.45
     keskus
    -0.45
    removeClass
    -0.44
     aikana
    -0.44
    POSITIVE LOGITS
    LookAnd
    0.82
     the
    0.73
     him
    0.69
    '][]
    0.68
     his
    0.68
     GenerationType
    0.68
     فريبيس
    0.66
     any
    0.63
     our
    0.62
     their
    0.60
    Activations Density 14.790%

    No Known Activations