© 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. 49760
    Prev
    Next
    INDEX
    Explanations

    code block formatting

    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
     ভাষণ
    0.40
     삼각형
    0.38
    填
    0.38
     завер
    0.37
     denaro
    0.37
     വരു
    0.36
    েক
    0.36
    銭
    0.36
     reconstit
    0.36
     완료
    0.35
    POSITIVE LOGITS
    elde
    0.39
     Ausdruck
    0.38
    selValue
    0.38
    귿
    0.37
    фере
    0.35
    zcz
    0.35
    zsche
    0.35
    chetto
    0.35
     боя
    0.34
    ългар
    0.34
    Activations Density 0.098%

    No Known Activations