© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60226
    Prev
    Next
    INDEX
    Explanations

    direct messages and social interactions

    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
    /
    0.51
    ;
    0.51
    ના
    0.51
     de
    0.48
    e
    0.46
     idling
    0.44
    Η
    0.44
    placement
    0.44
    ,
    0.44
    _
    0.44
    POSITIVE LOGITS
    v
    0.47
    zī
    0.46
    ಾವ್
    0.45
     recepción
    0.45
    ꞎ
    0.45
     अवार्ड
    0.44
    拭
    0.44
    ў
    0.43
     лекар
    0.43
    ﻰ
    0.43
    Activations Density 0.053%

    No Known Activations