© 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. 33758
    Prev
    Next
    INDEX
    Explanations

    Academy Award

    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
    i
    0.78
    ي
    0.75
     cheerfully
    0.61
     coarsely
    0.61
    '
    0.60
     لأ
    0.58
     يؤ
    0.58
    ed
    0.57
     unimagin
    0.57
     emphasise
    0.57
    POSITIVE LOGITS
    یت
    0.85
    ید
    0.76
    یس
    0.76
    ல்
    0.73
    یر
    0.65
    یش
    0.64
    する
    0.63
    گیری
    0.62
    یم
    0.62
    思議
    0.62
    Activations Density 0.000%

    No Known Activations