© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161497
    Prev
    Next
    INDEX
    Explanations

    retire early

    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_2_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
    r
    1.45
    te
    1.33
    š
    1.19
    し
    1.17
    rik
    1.13
    se
    1.13
    sp
    1.13
    ng
    1.09
    land
    1.09
    ref
    1.07
    POSITIVE LOGITS
    ри
    1.88
    ל
    1.73
    ாக
    1.39
    リ
    1.39
    ीय
    1.36
    ਾ
    1.35
    o
    1.31
    ST
    1.29
    ת
    1.29
    ী
    1.27
    Activations Density 0.000%

    No Known Activations