© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205285
    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_6_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
    s
    1.21
    ير
    1.18
    t
    1.16
    -
    1.16
    ó
    1.10
    ت
    1.02
     erinnert
    0.98
    \
    0.98
     Preise
    0.96
    _
    0.95
    POSITIVE LOGITS
     в
    1.09
    ın
    1.02
    도
    0.98
    ный
    0.93
     σε
    0.92
    nya
    0.92
    ใน
    0.92
    fluoro
    0.92
    의
    0.91
    ۰
    0.91
    Activations Density 0.000%

    No Known Activations