© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11427
    Prev
    Next
    INDEX
    Explanations

    equations, mathematical symbols, and specific variable names such as theta, psi, and phi

    oai_token-act-pair · gemini-2.0-flash

    non-English or special characters

    np_token-act-pair-logits · gpt-4o-mini

    mathematical formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     $\
    -0.81
    ="\
    -0.74
     للمعارف
    -0.70
    {$\
    -0.69
    }{$\
    -0.67
    OGND
    -0.67
     Î
    -0.66
    Î
    -0.65
    RenderAtEndOf
    -0.65
     alpha
    -0.64
    POSITIVE LOGITS
     XNUMX
    0.54
    بوابة
    0.45
     uș
    0.44
    !("{}",
    0.41
     fusca
    0.41
    УДК
    0.40
    GEBURTS
    0.39
    <sup>
    0.39
     = 
    0.38
     [],
    0.37
    Activations Density 1.813%

    No Known Activations