© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198871
    Prev
    Next
    INDEX
    Explanations

    we

    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_46_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
     prop
    0.42
    厥
    0.39
    šenje
    0.38
     leverage
    0.38
     swell
    0.38
    攢
    0.38
    ليو
    0.37
     물질
    0.37
    劃
    0.37
     শব্দটি
    0.37
    POSITIVE LOGITS
     remained
    0.47
    残
    0.43
     остались
    0.43
    Remain
    0.42
     orang
    0.42
    Remaining
    0.40
     remain
    0.39
     geworden
    0.39
     maps
    0.39
     accomplishing
    0.38
    Activations Density 0.002%

    No Known Activations