© 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. 38490
    Prev
    Next
    INDEX
    Explanations

    storage box format

    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
    ي
    0.75
    ે
    0.70
     הכ
    0.66
    OD
    0.65
     señal
    0.64
    يه
    0.63
     وأ
    0.62
     destac
    0.60
    也就是说
    0.60
    iť
    0.60
    POSITIVE LOGITS
    of
    0.70
    حت
    0.68
    د
    0.67
    It
    0.61
    ր
    0.61
    Ive
    0.60
    रा
    0.58
     It
    0.57
    تم
    0.55
    ধারণ
    0.55
    Activations Density 0.014%

    No Known Activations