© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 62517
    Prev
    Next
    INDEX
    Explanations

    Unsustainable

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    1.21
    et
    1.03
    al
    0.99
    ان
    0.96
    on
    0.81
    h
    0.69
    hift
    0.66
    en
    0.65
    eries
    0.61
    ystems
    0.61
    POSITIVE LOGITS
    ć
    0.50
    ཀ
    0.40
    ྩ
    0.40
    ै
    0.39
    cc
    0.36
    ಟ್ರ
    0.36
    পত্র
    0.35
    I
    0.35
    ීන්
    0.35
    cció
    0.34
    Activations Density 0.001%

    No Known Activations