© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 48880
    Prev
    Next
    INDEX
    Explanations

    return jsonify or json

    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_31_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
     Cam
    0.29
    стор
    0.27
     مهر
    0.27
     leuc
    0.27
     votos
    0.26
    ">→</
    0.26
     hangar
    0.26
     murs
    0.26
     Rit
    0.26
     tapis
    0.26
    POSITIVE LOGITS
    Restrictions
    0.31
    Address
    0.30
    我的
    0.28
     ezingu
    0.28
    seagreen
    0.28
    Training
    0.27
     ສ
    0.27
     genießen
    0.27
    js
    0.26
     Address
    0.26
    Activations Density 0.007%

    No Known Activations