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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6811
    Prev
    Next
    INDEX
    Explanations

    the word "attack" in varying contexts

    oai_token-act-pair · gemini-2.0-flash

    attack

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     CreateTagHelper
    -0.66
    DoubleQuotes
    -0.63
    ISupport
    -0.62
    getMinutes
    -0.58
    SequentialGroup
    -0.58
     Osbourne
    -0.56
    celotti
    -0.56
    ModelSerializer
    -0.55
    TypedDataSet
    -0.55
    ----------------
    -0.54
    POSITIVE LOGITS
     Monfieur
    1.11
     houſe
    0.97
     Efq
    0.95
     pleaſure
    0.93
     feroit
    0.93
     Majefty
    0.93
     ſta
    0.90
     ſche
    0.89
     auffi
    0.88
     avoient
    0.88
    Activations Density 1.238%

    No Known Activations