© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 257396
    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_22_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
    nl
    0.51
    onavirus
    0.48
    oflu
    0.47
    oning
    0.47
     ঘন
    0.46
    ون
    0.46
    zl
    0.46
    z
    0.46
    synthetic
    0.46
     diffusivity
    0.45
    POSITIVE LOGITS
     demonstrate
    0.54
     promote
    0.50
     Conservation
    0.49
    詎
    0.49
     Afternoon
    0.48
    ренности
    0.47
    ፈር
    0.47
     Visitor
    0.46
     waive
    0.46
     Confidential
    0.46
    Activations Density 0.000%

    No Known Activations