© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159906
    Prev
    Next
    INDEX
    Explanations

    berries and GER

    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
    an
    0.80
    ian
    0.80
    ע
    0.79
    $)$.
    0.76
    est
    0.68
    おい
    0.65
    is
    0.64
    are
    0.64
    }\}
    0.63
    -
    0.63
    POSITIVE LOGITS
    К
    0.92
    ana
    0.90
    ব
    0.85
    ख
    0.83
    Х
    0.82
    ы
    0.82
    ли
    0.81
    Це
    0.81
    Так
    0.80
    ỡng
    0.80
    Activations Density 0.001%

    No Known Activations