© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77850
    Prev
    Next
    INDEX
    Explanations

    multilingual names or labels

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_53_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
    zo
    0.79
    z
    0.74
    zn
    0.74
    ze
    0.73
    zu
    0.73
    zen
    0.69
    зе
    0.68
    zes
    0.67
    ζ
    0.66
    zele
    0.66
    POSITIVE LOGITS
    ীণ
    0.42
    ियों
    0.40
    Kita
    0.40
    Chúng
    0.40
    हमने
    0.39
    如果我们
    0.38
    াবণ
    0.38
     Larn
    0.37
    ぃ
    0.37
     kita
    0.37
    Activations Density 0.000%

    No Known Activations