© 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. 123242
    Prev
    Next
    INDEX
    Explanations

    championships and club penguin

    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
    ла
    0.91
     of
    0.79
    ul
    0.70
     месяца
    0.69
    یا
    0.68
    л
    0.68
    ing
    0.66
    ate
    0.66
     macron
    0.66
    ة
    0.64
    POSITIVE LOGITS
    Badge
    0.58
    getSize
    0.56
     ومت
    0.55
    竖
    0.54
    fight
    0.54
     않았
    0.54
     предстоя
    0.53
    তীত
    0.53
     Einf
    0.52
    and
    0.52
    Activations Density 0.001%

    No Known Activations