© 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. 134041
    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
    る
    1.27
     و
    1.16
     canister
    1.04
     parser
    1.01
     crab
    0.97
     server
    0.97
     bolt
    0.96
     cache
    0.95
     rhino
    0.95
     vendor
    0.93
    POSITIVE LOGITS
    ab
    1.24
    0
    1.23
    ments
    1.21
    íl
    1.17
    ra
    1.13
    н
    1.10
    𝟘
    1.10
    és
    1.09
    ík
    1.09
    jí
    1.07
    Activations Density 0.000%

    No Known Activations