© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 133243
    Prev
    Next
    INDEX
    Explanations

    Polish tokens: Targ, tekst

    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_6_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
    З
    1.46
    Т
    1.40
    С
    1.39
    ী
    1.35
    ف
    1.28
    Σ
    1.16
    İ
    1.13
    on
    1.13
    Ś
    1.09
    اف
    1.08
    POSITIVE LOGITS
    ro
    1.12
    с
    0.93
    ta
    0.92
    ក្នុង
    0.89
    q
    0.89
    res
    0.86
    who
    0.85
    лна
    0.84
    ๑
    0.81
    nya
    0.81
    Activations Density 0.000%

    No Known Activations