© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208301
    Prev
    Next
    INDEX
    Explanations

    heavily influenced by

    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
     players
    0.36
    )$;
    0.36
    ，“
    0.34
    ），
    0.34
    ላል
    0.34
    أي
    0.33
    手
    0.33
    ंजी
    0.33
    சில்
    0.33
    ថា
    0.32
    POSITIVE LOGITS
    烪
    0.39
    炵
    0.38
     egun
    0.38
     Haines
    0.37
    蟳
    0.36
    圤
    0.35
    thiophen
    0.35
     나의
    0.35
     sada
    0.35
    nemis
    0.34
    Activations Density 0.009%

    No Known Activations