© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 45376
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
     geométricas
    0.65
    ຢ່າງ
    0.65
    ম্
    0.65
    ла
    0.62
    入れて
    0.61
     médiocrement
    0.61
    σό
    0.61
    ב
    0.61
     matemáticas
    0.60
    ເລັກ
    0.59
    POSITIVE LOGITS
    en
    0.93
    um
    0.81
     It
    0.77
    ing
    0.68
    ik
    0.68
    u
    0.67
     for
    0.65
    uque
    0.64
    ee
    0.63
    in
    0.62
    Activations Density 0.000%

    No Known Activations