© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39301
    Prev
    Next
    INDEX
    Explanations

    off-the-beaten-path

    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_3_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
    Ну
    0.92
    У
    0.76
    Я
    0.76
    Υ
    0.72
    Под
    0.69
    ről
    0.69
    Ю
    0.68
    Για
    0.68
    Y
    0.67
    Ве
    0.66
    POSITIVE LOGITS
     Beat
    0.89
    in
    0.88
     beats
    0.86
    j
    0.86
    w
    0.86
     are
    0.84
    p
    0.79
    beat
    0.77
    Beat
    0.77
    u
    0.77
    Activations Density 0.001%

    No Known Activations