© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57715
    Prev
    Next
    INDEX
    Explanations

    degrees

    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_59_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
    ajos
    0.42
     unidades
    0.38
     सर्वि
    0.38
     temp
    0.37
    ameen
    0.36
    ?,?,
    0.36
     lames
    0.36
    谗
    0.36
    ເລັກ
    0.35
     categoryService
    0.35
    POSITIVE LOGITS
     ™
    0.65
     ®
    0.63
    ®
    0.63
    ™
    0.61
     $^{\
    0.59
    $^{
    0.57
     degree
    0.54
     kadar
    0.51
    ^{\
    0.50
    Degree
    0.50
    Activations Density 0.001%

    No Known Activations