© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12996
    Prev
    Next
    INDEX
    Explanations

    words that relate to scientific methodology and capabilities

    oai_token-act-pair · gemini-2.0-flash

    method

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     فريبيس
    -1.02
     <>",
    -0.82
    IsContent
    -0.81
    bootstrapcdn
    -0.80
    ScopeManager
    -0.79
     متعلقه
    -0.78
    󠁢
    -0.77
    onViewCreated
    -0.76
     greateſt
    -0.75
    AnchorStyles
    -0.72
    POSITIVE LOGITS
    <bos>
    1.79
    ↵↵
    0.98
    ↵
    0.77
    '
    0.73
      
    0.60
    is
    0.57
    in
    0.55
    an
    0.55
     to
    0.52
    <strong>
    0.52
    Activations Density 1.303%

    No Known Activations