© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65490
    Prev
    Next
    INDEX
    Explanations

    U.S.C. statute sections

    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_41_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
     STRAIGHT
    0.43
     straight
    0.42
     curto
    0.40
    straight
    0.39
    불
    0.37
     струк
    0.37
    Straight
    0.37
     unsus
    0.37
     القص
    0.35
    CTR
    0.35
    POSITIVE LOGITS
     ۳
    0.42
     ($\
    0.42
     ၁
    0.41
     Critique
    0.39
     ۲
    0.39
     ۵
    0.38
     ۶
    0.38
     শ্র
    0.38
     ۹
    0.37
    ---------*/
    0.36
    Activations Density 0.000%

    No Known Activations