© 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-3-27B-IT
    5. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 78787
    Prev
    Next
    INDEX
    Explanations

    code syntax delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_29_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ginger
    0.38
    痍
    0.36
    ભાર
    0.36
    Caso
    0.36
    ponenten
    0.35
     Annotated
    0.35
     Caso
    0.35
    繚
    0.35
     भरा
    0.35
    iniai
    0.35
    POSITIVE LOGITS
     вода
    0.40
     norm
    0.38
    FUNCION
    0.37
     Devils
    0.37
     криптовалю
    0.36
     watermark
    0.36
     neto
    0.36
     Poles
    0.36
     системати
    0.35
     yearn
    0.35
    Activations Density 0.001%

    No Known Activations