© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15913
    Prev
    Next
    INDEX
    Explanations

    code, scripts, and acronyms particularly 'SL'

    oai_token-act-pair · gemini-2.0-flash

    SL

    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
    <strong>
    -1.35
    (
    -1.31
     
    -1.31
    .
    -1.28
    _
    -1.26
    <b>
    -1.25
    d
    -1.25
      
    -1.25
    ↵
    -1.21
    a
    -1.21
    POSITIVE LOGITS
     Efq
    2.31
    ^(@)
    2.16
     myſelf
    2.08
     Мексичка
    1.97
     himſelf
    1.93
     Jefus
    1.92
     itſelf
    1.92
     photolibrary
    1.91
    NUMX
    1.90
     Theſe
    1.90
    Activations Density 5.357%

    No Known Activations