© 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. 77941
    Prev
    Next
    INDEX
    Explanations

    very small

    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
    uiscono
    0.43
     ভট্ট
    0.39
    帚
    0.39
    मित्व
    0.38
     пожи
    0.37
    心中的
    0.37
     উদ্বাস্ত
    0.37
    INFORM
    0.37
    城乡
    0.37
    BlackRatingDiff
    0.36
    POSITIVE LOGITS
     cens
    0.38
    lf
    0.37
    啶
    0.37
     प्रकाश
    0.34
     consum
    0.34
     tyle
    0.34
     sole
    0.34
     primitives
    0.33
     solos
    0.33
     skyl
    0.33
    Activations Density 0.000%

    No Known Activations