© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83554
    Prev
    Next
    INDEX
    Explanations

    custom

    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_0_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
     for
    1.92
    ल
    1.70
    G
    1.69
    J
    1.59
    一
    1.59
    K
    1.58
    Y
    1.55
    al
    1.49
    л
    1.49
    ن
    1.46
    POSITIVE LOGITS
    ’
    1.53
    ่
    1.50
    that
    1.38
    w
    1.16
     Caixa
    1.13
    ه‌
    1.12
    1.12
    ır
    1.11
    ના
    1.08
     Nascimento
    1.07
    Activations Density 0.002%

    No Known Activations