© 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. 18045
    Prev
    Next
    INDEX
    Explanations

    security updates and bug fixes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Radar
    0.40
    瑜
    0.40
     seizing
    0.39
     Modification
    0.37
    Modification
    0.36
    modification
    0.36
    RD
    0.36
    ณิต
    0.36
     runnable
    0.35
    葆
    0.35
    POSITIVE LOGITS
     correction
    0.52
    Correction
    0.50
     corrections
    0.49
     corrected
    0.49
     corrig
    0.47
     corrigir
    0.47
     patches
    0.47
     Corrections
    0.47
     correção
    0.45
    矯正
    0.45
    Activations Density 0.032%

    No Known Activations