© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195070
    Prev
    Next
    INDEX
    Explanations

    blemish / blemishes

    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_4_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
    as
    1.20
    ний
    1.09
    an
    1.04
    ’
    0.89
    ‌های
    0.89
    os
    0.88
    ent
    0.86
    about
    0.86
    ‌هایی
    0.86
    ari
    0.84
    POSITIVE LOGITS
    ف
    1.34
     to
    1.27
    ك
    1.21
    د
    1.16
    ו
    1.14
    k
    1.13
    ض
    1.13
    d
    1.10
    g
    1.10
    u
    1.02
    Activations Density 0.000%

    No Known Activations