© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9640
    Prev
    Next
    INDEX
    Explanations

    a mixture of code-related terms and Portugese words.

    oai_token-act-pair · gemini-2.0-flash

    CDATA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    </thead>
    -0.68
    허
    -0.62
     nod
    -0.57
    correre
    -0.57
     Besøkt
    -0.54
     Nod
    -0.51
    chaub
    -0.49
    hope
    -0.49
     hope
    -0.49
    Koordin
    -0.49
    POSITIVE LOGITS
     ModelExpression
    0.81
    VIAF
    0.68
    цездатний
    0.66
    bewerken
    0.63
    enderror
    0.63
     Himo
    0.62
     ExecuteAsync
    0.62
    ッズ
    0.60
     autem
    0.58
    ptonshire
    0.58
    Activations Density 12.615%

    No Known Activations