© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62706
    Prev
    Next
    INDEX
    Explanations

    Divides

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    Base
    0.42
    RIM
    0.39
    B
    0.39
     introduces
    0.38
    с
    0.38
    Tape
    0.38
     Base
    0.38
     Supreme
    0.37
    ם
    0.37
    Ck
    0.36
    POSITIVE LOGITS
    ciendo
    0.39
    ющего
    0.38
     ব্র্যান্ড
    0.38
    品牌的
    0.38
    เด
    0.37
    ಾದರೂ
    0.37
    ilgan
    0.36
    ួក
    0.36
     BRAND
    0.35
    isnan
    0.35
    Activations Density 0.000%

    No Known Activations