© 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. 5472
    Prev
    Next
    INDEX
    Explanations

    the word "head."

    oai_token-act-pair · gemini-2.0-flash

    head

    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
     
    -1.23
    <eos>
    -1.08
     (
    -0.99
    ,
    -0.94
    <strong>
    -0.90
     [
    -0.88
     $
    -0.87
     "
    -0.86
     “
    -0.86
    ↵↵
    -0.85
    POSITIVE LOGITS
     Efq
    2.05
     myſelf
    1.84
     Monfieur
    1.82
     Jefus
    1.70
     itſelf
    1.70
     Theſe
    1.67
    ^(@)
    1.63
     Majefty
    1.55
     photolibrary
    1.55
     himſelf
    1.54
    Activations Density 1.701%

    No Known Activations