© 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. 6822
    Prev
    Next
    INDEX
    Explanations

    words describing something being pleasant, or units of measure

    oai_token-act-pair · gemini-2.0-flash

    measurements/physical descriptions

    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
     
    -0.87
     (
    -0.84
     I
    -0.77
    <eos>
    -0.76
    ,
    -0.73
     a
    -0.73
     to
    -0.71
     P
    -0.69
    t
    -0.69
    .
    -0.69
    POSITIVE LOGITS
     myſelf
    1.78
     itſelf
    1.77
     Majefty
    1.63
     pleaſure
    1.63
     Efq
    1.59
     themſelves
    1.56
     Jefus
    1.55
     Reſ
    1.52
     Diſ
    1.51
     ſtate
    1.50
    Activations Density 1.615%

    No Known Activations