© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13336
    Prev
    Next
    INDEX
    Explanations

    references to prior or external material, or other points outside the current scope

    oai_token-act-pair · 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
    Negative Logits
     صوتيه
    -0.78
    theless
    -0.70
    выше
    -0.65
     aikaa
    -0.65
    ⓘ
    -0.63
     priori
    -0.62
    oubtedly
    -0.60
    wixt
    -0.60
     sobra
    -0.59
     vastaan
    -0.58
    POSITIVE LOGITS
     onOptions
    0.56
     linkovi
    0.55
    ResponseWriter
    0.52
    Pictured
    0.51
    ็จ
    0.51
     utafiti
    0.49
    fromCharCode
    0.48
    igslist
    0.47
    новниш
    0.47
    DeclareMath
    0.47
    Activations Density 1.204%

    No Known Activations