© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204449
    Prev
    Next
    INDEX
    Explanations

    game

    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_6_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
     for
    0.47
    كتب
    0.42
    ow
    0.42
     been
    0.41
    قيم
    0.41
     إ
    0.41
     el
    0.39
    źdz
    0.39
     llamas
    0.39
     was
    0.39
    POSITIVE LOGITS
    สามารถ
    0.54
    ا
    0.50
    ur
    0.48
    g
    0.48
    ла
    0.47
    น้ำ
    0.47
    นา
    0.47
    lar
    0.46
    들이
    0.46
    ul
    0.44
    Activations Density 0.000%

    No Known Activations