© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 89059
    Prev
    Next
    INDEX
    Explanations

    reddish glow or back holes

    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_11_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
    地的
    0.50
    落
    0.48
    喹
    0.47
     THAT
    0.47
    логии
    0.47
    的地
    0.46
     ABSTRACT
    0.46
    폈
    0.46
    ভাবে
    0.45
    太
    0.45
    POSITIVE LOGITS
     creators
    0.53
     externalities
    0.51
     chessboard
    0.50
     corroborate
    0.50
     probability
    0.49
     t
    0.49
     oscillations
    0.48
     purity
    0.48
     redshift
    0.48
     namespaces
    0.47
    Activations Density 0.000%

    No Known Activations