© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132562
    Prev
    Next
    INDEX
    Explanations

    Fidelity, Schwab, SoFi

    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_1_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
    ü
    1.27
    1.11
    ری
    0.97
     I
    0.93
     faç
    0.92
    一个
    0.92
    ри
    0.91
    ية
    0.91
    ай
    0.90
     c
    0.90
    POSITIVE LOGITS
    ק
    1.46
    ب
    1.28
    ס
    1.27
    ق
    1.24
    d
    1.23
    ו
    1.20
    та
    1.19
    t
    1.17
    u
    1.17
    the
    1.16
    Activations Density 0.000%

    No Known Activations