© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220014
    Prev
    Next
    INDEX
    Explanations

    reading data streams

    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_31_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
     stopper
    0.42
     trader
    0.40
    prex
    0.40
    xtime
    0.39
     merkle
    0.39
    rbrack
    0.38
    苣
    0.37
    祷
    0.37
     Bounds
    0.37
    Bounding
    0.37
    POSITIVE LOGITS
     LED
    0.39
    READ
    0.36
    јо
    0.35
    ulosic
    0.34
     প্রতিক্রিয়া
    0.33
    读
    0.32
    事務
    0.32
    خوان
    0.32
     ван
    0.32
     Woodland
    0.32
    Activations Density 0.000%

    No Known Activations