© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197744
    Prev
    Next
    INDEX
    Explanations

    quick overview

    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_4_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
    0.95
    at
    0.80
    og
    0.73
    are
    0.70
    ა
    0.69
    ali
    0.68
    am
    0.66
    he
    0.66
    as
    0.64
    ie
    0.63
    POSITIVE LOGITS
    До
    0.80
    ಸ
    0.77
    세계
    0.77
    >
    0.77
    Ме
    0.76
    Від
    0.75
    Մ
    0.73
    １
    0.73
    بر
    0.71
    Са
    0.71
    Activations Density 0.000%

    No Known Activations