© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 29674
    Prev
    Next
    INDEX
    Explanations

    cross-cutting

    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
    IRE
    0.74
     netizens
    0.72
    ari
    0.70
     里
    0.69
    ARY
    0.68
     مُ
    0.68
     tortoise
    0.68
     장애
    0.66
     carbohydrate
    0.66
     monasteries
    0.66
    POSITIVE LOGITS
    k
    0.94
    n
    0.90
    can
    0.77
    c
    0.75
    nın
    0.74
    b
    0.73
    gın
    0.72
    pada
    0.71
    )
    0.71
    driven
    0.67
    Activations Density 0.001%

    No Known Activations