© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 79148
    Prev
    Next
    INDEX
    Explanations

    repetition_penalty numerical values

    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_31_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
     المجموعة
    0.44
     Nguyễn
    0.38
    GCG
    0.38
    润
    0.38
    ကြည်
    0.38
    grupo
    0.37
     González
    0.36
    潤
    0.36
     گروپ
    0.36
    梦想
    0.36
    POSITIVE LOGITS
     soliton
    0.38
     pill
    0.38
     Breton
    0.38
    %@",
    0.38
     stricter
    0.37
     blooms
    0.37
     ಕ
    0.37
     stale
    0.36
    astotal
    0.36
     Strict
    0.36
    Activations Density 0.001%

    No Known Activations