© 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. 24816
    Prev
    Next
    INDEX
    Explanations

    comparison table features

    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
    '
    0.96
     A
    0.93
     I
    0.80
     E
    0.70
     T
    0.67
    的核心
    0.66
     THAT
    0.65
    HT
    0.64
     that
    0.63
     Showing
    0.63
    POSITIVE LOGITS
     غیر
    0.76
    شی
    0.70
     نیز
    0.70
    தள
    0.70
    ضی
    0.69
    an
    0.69
    have
    0.69
    테
    0.68
     شخصی
    0.67
     یقین
    0.67
    Activations Density 0.002%

    No Known Activations