© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 214629
    Prev
    Next
    INDEX
    Explanations

    строка, срок, коммер, прогно, кван

    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_5_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
    ściej
    1.08
    ن
    1.02
    zieć
    0.98
    ită
    0.97
    نید
    0.95
    िज्या
    0.95
    ;
    0.93
    tida
    0.92
    śla
    0.90
    ン
    0.90
    POSITIVE LOGITS
     a
    1.35
    ל
    1.33
     It
    1.21
    CH
    1.16
    IS
    1.10
    ü
    1.07
    O
    1.05
    J
    1.05
     You
    1.04
    EX
    1.02
    Activations Density 0.000%

    No Known Activations