© 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. 38261
    Prev
    Next
    INDEX
    Explanations

    not just

    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
     می
    0.73
    ων
    0.65
    上げ
    0.63
     μην
    0.63
    خ
    0.62
     بی
    0.61
    الی
    0.60
    cı
    0.60
    ίναι
    0.59
    aları
    0.59
    POSITIVE LOGITS
    s
    0.73
    or
    0.70
    тся
    0.69
    ្សែ
    0.66
    et
    0.64
     Amenities
    0.64
    5
    0.63
    did
    0.63
    มาร
    0.62
    für
    0.61
    Activations Density 0.010%

    No Known Activations