© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 207071
    Prev
    Next
    INDEX
    Explanations

    attendees, expert, Game Participants

    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_20_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
     condesc
    0.43
     pipe
    0.42
    㧕
    0.40
    قطه
    0.39
    큽
    0.39
     rough
    0.39
     کھیلتے
    0.39
     misog
    0.38
     sozinha
    0.38
    ໊
    0.37
    POSITIVE LOGITS
     Biod
    0.43
    BUND
    0.42
     மற்றும்
    0.41
     Syr
    0.40
    বি
    0.39
    wj
    0.39
     এবং
    0.39
    na
    0.39
     Ottawa
    0.38
     Patterson
    0.38
    Activations Density 0.000%

    No Known Activations