© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13199
    Prev
    Next
    INDEX
    Explanations

    words ending in "ges" or related to foreign languages or scientific terms

    oai_token-act-pair · gemini-2.0-flash

    code and foreign languages

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ges
    -0.85
    ž
    -0.76
     же
    -0.63
    cer
    -0.63
    же
    -0.62
    ж
    -0.59
    ży
    -0.57
    ching
    -0.54
    cers
    -0.54
    жи
    -0.52
    POSITIVE LOGITS
    MathML
    0.84
    NUMX
    0.69
    ">@
    0.63
    XtraGrid
    0.63
     виправивши
    0.62
    ussis
    0.60
     Credo
    0.59
    sizeCache
    0.59
    roppo
    0.59
    ̙
    0.59
    Activations Density 3.181%

    No Known Activations