© 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. 108199
    Prev
    Next
    INDEX
    Explanations

    Zuni, Zazen, Zelt

    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
    ۰
    1.07
    ,
    1.05
    ini
    0.89
    ่
    0.82
    тся
    0.80
    inį
    0.78
    हरूको
    0.76
     потеря
    0.73
    вати
    0.72
    
    0.71
    POSITIVE LOGITS
    on
    1.61
    та
    1.56
    C
    1.51
    P
    1.51
    R
    1.51
    F
    1.50
    H
    1.50
    N
    1.45
    S
    1.43
    K
    1.43
    Activations Density 0.000%

    No Known Activations