© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 178109
    Prev
    Next
    INDEX
    Explanations

    T & N stage, Twitter, Approximation algorithm

    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_24_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
     Epile
    0.55
     σύ
    0.53
     液
    0.51
    ⌯
    0.50
     fetal
    0.50
     OPEC
    0.49
     Hangzhou
    0.49
     Vich
    0.49
     Polity
    0.49
     eksp
    0.49
    POSITIVE LOGITS
    Remember
    0.44
    directed
    0.43
    (`${
    0.39
     radii
    0.38
    around
    0.38
    ![](
    0.38
     profundizar
    0.38
    一顆
    0.37
    Hunt
    0.36
    ([
    0.36
    Activations Density 0.000%

    No Known Activations