© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178113
    Prev
    Next
    INDEX
    Explanations

    commands and

    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_29_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
     جگہ
    0.30
    LoginActivity
    0.29
    िटीज
    0.28
    숩
    0.28
    LLING
    0.28
    ॉड
    0.27
    esha
    0.27
     மனை
    0.27
     busier
    0.27
     Noodles
    0.27
    POSITIVE LOGITS
     מה
    0.32
     सैल
    0.31
    诞
    0.31
    絖
    0.31
    Compiled
    0.30
    最后的
    0.30
     reich
    0.30
    ABEL
    0.30
     programmatic
    0.29
    洌
    0.29
    Activations Density 0.000%

    No Known Activations