© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 48942
    Prev
    Next
    INDEX
    Explanations

    wombat

    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_10_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
     Л
    0.67
     tecnologie
    0.66
     Și
    0.64
     Германия
    0.63
     muszą
    0.63
     ойнойт
    0.63
     reação
    0.63
    itatea
    0.62
     Ș
    0.62
     পালন
    0.58
    POSITIVE LOGITS
    n
    0.98
    m
    0.95
    p
    0.94
    s
    0.89
    g
    0.80
    l
    0.80
    b
    0.76
    er
    0.74
    ic
    0.65
    d
    0.65
    Activations Density 0.000%

    No Known Activations