© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35471
    Prev
    Next
    INDEX
    Explanations

    want to know

    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_31_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
     föl
    0.39
     lookup
    0.38
     embe
    0.38
    ര്‍ത്ത
    0.37
     EGA
    0.37
    uque
    0.37
    躲
    0.37
     وعرف
    0.36
     геометри
    0.36
     begr
    0.34
    POSITIVE LOGITS
    症
    0.40
    씀
    0.40
    உங்கள்
    0.38
     nature
    0.36
    勁
    0.36
     espirit
    0.36
    (""
    0.35
    您的
    0.35
    优势
    0.35
     findPlayer
    0.34
    Activations Density 0.009%

    No Known Activations