© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54397
    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_30_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
     بول
    0.39
    Keith
    0.38
     King
    0.38
     Keith
    0.35
    Unis
    0.35
    RefCount
    0.35
     Brentwood
    0.35
    ث
    0.35
     Robinson
    0.35
    Paul
    0.34
    POSITIVE LOGITS
     próprios
    0.44
     procedimientos
    0.42
     teorema
    0.42
    urface
    0.40
     porque
    0.40
     árv
    0.40
     tomo
    0.40
     perché
    0.40
     objetivos
    0.39
    ulação
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.