© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197410
    Prev
    Next
    INDEX
    Explanations

    quality indicators

    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_4_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
    _
    1.17
    k
    0.90
    ING
    0.86
    t
    0.84
     manicure
    0.82
     handcuffed
    0.81
    y
    0.80
     glued
    0.78
     cuatro
    0.77
     prins
    0.76
    POSITIVE LOGITS
    in
    0.92
    સ
    0.85
    م
    0.84
    ب
    0.73
    ствия
    0.72
    IN
    0.70
    is
    0.68
    Set
    0.66
    ان
    0.66
    baiki
    0.66
    Activations Density 0.003%

    No Known Activations