© 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. 6745
    Prev
    Next
    INDEX
    Explanations

    parenthesized lists, or comma separated elements within a math environment, or a question and answer block

    oai_token-act-pair · gemini-2.0-flash

    comma

    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
     ,
    -2.13
     ,
    -1.34
     ,"
    -1.33
     ,\
    -1.27
    TagMode
    -1.22
     ,,
    -1.20
     ,'
    -1.20
    ，
    -1.17
     ，
    -1.15
     Efq
    -1.15
    POSITIVE LOGITS
    <bos>
    0.69
     a
    0.59
     it
    0.57
     is
    0.57
     in
    0.56
     the
    0.55
     u
    0.54
    y
    0.54
     all
    0.54
     (
    0.52
    Activations Density 1.341%

    No Known Activations