© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33785
    Prev
    Next
    INDEX
    Explanations

    api and shops

    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_3_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
    .
    0.82
    ار
    0.73
    "
    0.71
    2
    0.70
    (
    0.67
    ла
    0.65
    th
    0.63
    人
    0.63
    ли
    0.62
    يد
    0.61
    POSITIVE LOGITS
    u
    0.62
    an
    0.61
    ων
    0.61
    سازی
    0.61
    ו
    0.59
    ین
    0.59
     Togo
    0.58
     it
    0.57
    הר
    0.57
    جہ
    0.57
    Activations Density 0.002%

    No Known Activations