© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242422
    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_40_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
    Now
    0.47
     Now
    0.43
     убий
    0.42
    Теперь
    0.39
    NOW
    0.38
    寫
    0.38
    捛
    0.36
    ᱗
    0.36
     теперь
    0.36
     NOW
    0.35
    POSITIVE LOGITS
     support
    0.44
     suport
    0.40
    ᓇ
    0.39
     inapplicable
    0.38
     labeling
    0.36
     recommending
    0.36
     over
    0.36
     हरकत
    0.35
    newParameter
    0.35
    york
    0.35
    Activations Density 0.000%

    No Known Activations