© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32552
    Prev
    Next
    INDEX
    Explanations

    query parameters or variable names

    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_40_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
    羡
    0.41
     livros
    0.41
    Books
    0.41
    etés
    0.40
    .$;
    0.40
    $;
    0.38
     رسول
    0.37
    ॉर्ड
    0.37
     libros
    0.37
    図
    0.37
    POSITIVE LOGITS
     Morty
    0.38
    ńcz
    0.38
     टोट
    0.37
     설치
    0.37
    ưa
    0.36
     Antit
    0.36
     kappa
    0.35
     CCR
    0.34
    搭
    0.34
    out
    0.34
    Activations Density 0.000%

    No Known Activations