© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57861
    Prev
    Next
    INDEX
    Explanations

    say g

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
     g
    3.33
     г
    2.45
     ग
    1.77
     গ
    1.70
     گ
    1.68
    g
    1.59
     ג
    1.41
    ｇ
    1.38
    𝑔
    1.24
     గ
    1.18
    POSITIVE LOGITS
     والغ
    0.73
    GU
    0.58
    GOT
    0.57
    GA
    0.55
    GER
    0.54
    GG
    0.52
    GAM
    0.51
    GL
    0.50
    GEN
    0.50
    ГИ
    0.50
    Activations Density 0.043%

    No Known Activations