© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14639
    Prev
    Next
    INDEX
    Explanations

    code that is not particularly idiomatic

    oai_token-act-pair · gemini-2.0-flash

    Code configurations and variable names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    олові
    -0.75
    tagHelperRunner
    -0.75
    ngdoc
    -0.68
    adpleegd
    -0.65
    ьаж
    -0.62
    StandardCharsets
    -0.60
    xsi
    -0.59
    jsonwebtoken
    -0.59
    TintMode
    -0.58
     ExecuteAsync
    -0.57
    POSITIVE LOGITS
     termica
    0.58
     financières
    0.49
     bär
    0.49
     térm
    0.49
     remonte
    0.46
     nemici
    0.46
     origem
    0.46
     decât
    0.44
     sauvages
    0.44
     fata
    0.43
    Activations Density 2.209%

    No Known Activations