© 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. 39677
    Prev
    Next
    INDEX
    Explanations

    jelly bean and jellyfish

    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
    a
    0.77
    n
    0.65
    en
    0.64
    September
    0.57
    0
    0.57
    ce
    0.55
    0.54
    ing
    0.53
    de
    0.52
    an
    0.51
    POSITIVE LOGITS
    ’।
    0.70
    ції
    0.68
    '।
    0.67
    نے
    0.64
    در
    0.63
    --’
    0.63
    нов
    0.62
    пу
    0.60
    ку
    0.60
    objects
    0.59
    Activations Density 0.000%

    No Known Activations