© 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. 29304
    Prev
    Next
    INDEX
    Explanations

    open to

    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
    f
    0.93
    v
    0.73
    ین
    0.72
    w
    0.71
    いた
    0.66
    s
    0.66
    c
    0.64
    ной
    0.64
     buvo
    0.64
     要
    0.63
    POSITIVE LOGITS
     a
    0.73
     o
    0.73
     mink
    0.70
    ε
    0.70
     Teflon
    0.67
     Epsom
    0.67
    ները
    0.66
     u
    0.65
    :
    0.65
    را
    0.64
    Activations Density 0.041%

    No Known Activations