© 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. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 97617
    Prev
    Next
    INDEX
    Explanations

    your file path

    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_14_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
     disfruta
    0.61
     reluctantly
    0.59
     mighty
    0.58
    acart
    0.52
     Kiến
    0.52
     manta
    0.51
     workmen
    0.50
    .$;
    0.50
     chuva
    0.50
     disfrutar
    0.49
    POSITIVE LOGITS
    bet
    0.64
    ال
    0.62
    ر
    0.62
    st
    0.61
    ار
    0.61
    ger
    0.61
    ch
    0.60
    渽
    0.60
    ber
    0.59
    د
    0.59
    Activations Density 0.005%

    No Known Activations