© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16200
    Prev
    Next
    INDEX
    Explanations

    a mix of things like code, science jargon, interjections, and formatting characters.

    oai_token-act-pair · gemini-2.0-flash

    dashes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     analysed
    -0.54
     realised
    -0.54
     recognised
    -0.52
     behaviour
    -0.52
    ё
    -0.50
     dispon
    -0.50
    Aluminium
    -0.49
     colours
    -0.49
    inc
    -0.49
     realisation
    -0.48
    POSITIVE LOGITS
     nahilalakip
    1.13
    AndEndTag
    1.01
     iprot
    0.78
     ་་
    0.77
    addCriterion
    0.77
     Efq
    0.77
     esternos
    0.76
    Erreferentziak
    0.74
    findpost
    0.73
     themſelves
    0.73
    Activations Density 5.338%

    No Known Activations