© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61878
    Prev
    Next
    INDEX
    Explanations

    review our/my/your

    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_11_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
    𝐞
    0.71
    υσ
    0.68
    ли
    0.65
    o
    0.64
    ни
    0.62
     صدي
    0.62
    форд
    0.62
    ρι
    0.61
    getCql
    0.61
    鷸
    0.61
    POSITIVE LOGITS
    at
    0.66
    Ö
    0.64
    nt
    0.60
    Ç
    0.60
    int
    0.57
    Α
    0.57
    inin
    0.57
    Ř
    0.57
    İ
    0.56
    ¡
    0.56
    Activations Density 0.004%

    No Known Activations