© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 61168
    Prev
    Next
    INDEX
    Explanations

    newly minted tokens or people

    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_11_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
     ше
    0.55
    cule
    0.54
     в
    0.53
    ໃຊ
    0.50
    こうした
    0.49
     типов
    0.48
     статьи
    0.48
     и
    0.47
     функ
    0.47
     সেগুলি
    0.47
    POSITIVE LOGITS
     prédio
    0.48
     Alors
    0.47
    然後
    0.47
    陵
    0.46
    最佳
    0.45
     嗯
    0.45
     zrobić
    0.44
    纹
    0.44
    鳶
    0.44
    atown
    0.44
    Activations Density 0.000%

    No Known Activations