© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 179828
    Prev
    Next
    INDEX
    Explanations

    FE

    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_24_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
     विल
    0.37
     conno
    0.35
    লী
    0.35
     percussion
    0.35
    <0xA8>
    0.35
     //}
    0.34
     estate
    0.33
    キッチン
    0.33
    ,",
    0.33
     booty
    0.33
    POSITIVE LOGITS
     гуляць
    0.43
     एक्
    0.40
    𝐱
    0.39
    anedi
    0.39
    йдз
    0.39
    歙
    0.39
     sebanyak
    0.38
    <unused1757>
    0.38
     бясплатна
    0.38
    虎
    0.38
    Activations Density 0.000%

    No Known Activations