© 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. 86739
    Prev
    Next
    INDEX
    Explanations

    Zidane or console

    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
    ጋገብ
    0.71
    .},
    0.68
    id
    0.65
     আওতায়
    0.63
     flavored
    0.59
    ación
    0.59
    を紹介
    0.59
    ſs
    0.57
    oids
    0.57
     অধিনায়ক
    0.57
    POSITIVE LOGITS
    A
    0.88
    H
    0.86
    se
    0.84
    ל
    0.80
    ل
    0.78
    lah
    0.78
    db
    0.76
    di
    0.75
    ৮
    0.75
    deki
    0.75
    Activations Density 0.000%

    No Known Activations