© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 203230
    Prev
    Next
    INDEX
    Explanations

    principle and related concepts

    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_12_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
    generalized
    0.63
    ứng
    0.62
     espécie
    0.60
    vér
    0.59
     than
    0.57
     niż
    0.56
    л
    0.55
    ဲ
    0.55
    ETF
    0.55
    o
    0.55
    POSITIVE LOGITS
    ’
    0.58
     historians
    0.55
     aerob
    0.55
     areas
    0.54
     scholars
    0.54
     antigens
    0.52
     historias
    0.52
     Temple
    0.51
     attr
    0.50
     bisque
    0.50
    Activations Density 0.000%

    No Known Activations