© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 241757
    Prev
    Next
    INDEX
    Explanations

    markup labels or metadata

    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_25_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
    {~
    0.39
     Witcher
    0.39
     Interact
    0.38
    isalpha
    0.37
     wicket
    0.36
     UN
    0.35
    [
    0.35
     Sinh
    0.35
    ift
    0.34
     Jur
    0.34
    POSITIVE LOGITS
    Aerial
    0.42
     delicious
    0.38
     betreff
    0.38
    Delicious
    0.38
     caminando
    0.37
     donde
    0.36
     refills
    0.36
     tricks
    0.36
    😝
    0.36
    ানির
    0.36
    Activations Density 0.002%

    No Known Activations