© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129469
    Prev
    Next
    INDEX
    Explanations

    qubit and Qubes OS

    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_1_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
    ون
    1.35
    ل
    1.30
    ur
    1.25
    。
    1.22
    ol
    1.09
    ри
    1.02
    I
    1.01
    al
    1.00
    ai
    1.00
    erb
    0.99
    POSITIVE LOGITS
    न
    1.29
    u
    1.19
    .’”
    1.04
    ಸ್ತಕ
    1.03
    ą
    1.02
    nya
    0.99
    н
    0.99
    IN
    0.98
    ন
    0.95
     laureate
    0.94
    Activations Density 0.002%

    No Known Activations