© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20940
    Prev
    Next
    INDEX
    Explanations

    align

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    unków
    0.35
    ,*
    0.35
    _(
    0.35
    /(
    0.34
    зит
    0.34
    Sol
    0.34
    פק
    0.33
    魅
    0.33
     \*
    0.33
     últimas
    0.33
    POSITIVE LOGITS
     directions
    0.53
    Direction
    0.51
    directions
    0.50
     direcciones
    0.50
     Direction
    0.49
     direction
    0.49
    direction
    0.48
     items
    0.47
    方向
    0.47
     दिशा
    0.46
    Activations Density 0.002%

    No Known Activations