© 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. 6705
    Prev
    Next
    INDEX
    Explanations

    adjectives expressing actions happening in time, often related to observation or emotions

    oai_token-act-pair · gemini-2.0-flash

    suddenly

    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
    -1.79
     Houſe
    -1.48
     Jefus
    -1.41
     Theſe
    -1.35
     myſelf
    -1.34
     Eſ
    -1.34
     Shakspeare
    -1.33
     Reſ
    -1.30
    endphp
    -1.27
     raiſ
    -1.27
    POSITIVE LOGITS
     the
    0.91
     more
    0.73
     a
    0.72
    ,
    0.71
     in
    0.71
     very
    0.71
     an
    0.68
     as
    0.65
     
    0.63
     her
    0.62
    Activations Density 2.171%

    No Known Activations