© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 84252
    Prev
    Next
    INDEX
    Explanations

    times greater or of a specific quantity

    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_23_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
     politič
    0.39
    esthesia
    0.39
     tribu
    0.38
     Nim
    0.38
     Surgery
    0.38
     About
    0.37
     Trailer
    0.36
    艇
    0.36
     trib
    0.36
     POLITICAL
    0.36
    POSITIVE LOGITS
    かの
    0.39
     cron
    0.38
     menciptakan
    0.38
     alc
    0.38
    創建
    0.38
    regen
    0.38
     создавать
    0.38
     iemand
    0.37
    涧
    0.37
    ەکە
    0.36
    Activations Density 0.002%

    No Known Activations