© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57120
    Prev
    Next
    INDEX
    Explanations

    credit and credits

    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_11_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
    '`--
    0.70
     እንቅስቃሴ
    0.69
    краё
    0.67
    vaegir
    0.63
    gheatmap
    0.59
    跚
    0.59
    єте
    0.59
    ’
    0.59
    سٹ
    0.59
    armée
    0.59
    POSITIVE LOGITS
    ↵↵
    0.75
     a
    0.72
    ER
    0.70
    M
    0.69
    a
    0.65
    6
    0.64
     Fire
    0.63
     was
    0.63
     Ice
    0.61
     investment
    0.60
    Activations Density 0.001%

    No Known Activations