© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 88739
    Prev
    Next
    INDEX
    Explanations

    sim

    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_60_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
    i
    0.57
    iénd
    0.49
    ে
    0.49
    aboration
    0.48
    iola
    0.47
    لاً
    0.46
    ieth
    0.46
    يلا
    0.44
    m
    0.44
    يًا
    0.43
    POSITIVE LOGITS
     ע
    0.53
     u
    0.43
    ர
    0.41
    ת
    0.40
    ִי
    0.38
     lo
    0.37
     у
    0.37
     മന
    0.37
     simulated
    0.37
    u
    0.37
    Activations Density 0.001%

    No Known Activations