© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107565
    Prev
    Next
    INDEX
    Explanations

    more ... than

    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_2_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
    ad
    1.01
    т
    1.01
    い
    1.00
    ী
    0.98
    it
    0.97
    மாக
    0.92
    et
    0.90
    .
    0.90
     the
    0.90
    ів
    0.88
    POSITIVE LOGITS
    ند
    0.82
     позволи
    0.72
    ל
    0.71
    0
    0.71
    cknowled
    0.69
    that
    0.68
    ↵↵
    0.67
     найд
    0.66
    一脸
    0.66
     нажа
    0.66
    Activations Density 0.002%

    No Known Activations