© 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. 2985
    Prev
    Next
    INDEX
    Explanations

    words or parts of words commonly found in technical documents

    oai_token-act-pair · gemini-2.0-flash

    inc

    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
    Negative Logits
    inc
    -0.97
    one
    -0.84
    old
    -0.82
    inn
    -0.80
    up
    -0.79
    un
    -0.79
    int
    -0.77
    anti
    -0.77
    ink
    -0.77
    id
    -0.74
    POSITIVE LOGITS
     us
    0.70
    exécution
    0.64
     ins
    0.64
     un
    0.63
    notag
    0.63
     im
    0.62
    interprétation
    0.61
    iotti
    0.60
    étape
    0.58
    extré
    0.58
    Activations Density 3.296%

    No Known Activations