© 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. 7926
    Prev
    Next
    INDEX
    Explanations

    the word "shut"

    oai_token-act-pair · gemini-2.0-flash

    shut

    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
     Efq
    -2.11
     myſelf
    -1.95
     itſelf
    -1.91
     pleaſure
    -1.83
     Majefty
    -1.82
     Reſ
    -1.81
     Jefus
    -1.79
     Anſ
    -1.79
     poffe
    -1.77
     purpoſe
    -1.75
    POSITIVE LOGITS
     the
    0.89
     
    0.81
     I
    0.75
     J
    0.74
     "
    0.73
     $
    0.68
    ↵↵
    0.68
     several
    0.66
     a
    0.63
     P
    0.63
    Activations Density 1.189%

    No Known Activations