© 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. 162043
    Prev
    Next
    INDEX
    Explanations

    in this essay/article/video

    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
    บัน
    0.37
     דער
    0.37
    commands
    0.36
    命令
    0.36
     command
    0.34
     commands
    0.34
     /,
    0.34
    वण्यात
    0.34
     TLR
    0.34
    ポール
    0.33
    POSITIVE LOGITS
     menyebut
    0.43
    เบ
    0.40
     ежедневно
    0.38
    닦
    0.38
     бе
    0.37
     ежеднев
    0.37
     insure
    0.37
     scratching
    0.36
     Hygien
    0.36
     opinión
    0.36
    Activations Density 0.000%

    No Known Activations