© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 80594
    Prev
    Next
    INDEX
    Explanations

    bleed or bleeding

    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_0_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
    u
    1.81
    r
    1.74
    a
    1.56
    0
    1.53
    i
    1.49
    t
    1.46
    ี
    1.45
    b
    1.45
    f
    1.40
    し
    1.30
    POSITIVE LOGITS
    ك
    2.09
    ح
    1.56
    ع
    1.51
    تك
    1.38
    الى
    1.37
    فير
    1.37
    ла
    1.36
     jede
    1.35
     بيانات
    1.34
    স
    1.34
    Activations Density 0.000%

    No Known Activations