© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226227
    Prev
    Next
    INDEX
    Explanations

    distributor

    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_10_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
    IN
    0.75
    ن
    0.73
    t
    0.62
    น
    0.61
    ות
    0.59
     selben
    0.59
     zasi
    0.57
    سي
    0.56
    ات
    0.55
    Um
    0.55
    POSITIVE LOGITS
     reckless
    0.72
    posición
    0.71
    ވެ
    0.71
    pregnant
    0.71
    står
    0.66
    ﮐ
    0.66
    ступи
    0.64
    アンド
    0.64
    ptosis
    0.64
    goes
    0.63
    Activations Density 0.009%

    No Known Activations