© 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. 75290
    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_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
    рои
    0.40
     홈페이지
    0.40
    Website
    0.39
    苃
    0.39
     оптима
    0.38
    ovia
    0.37
     tableName
    0.37
     മി
    0.37
    中美
    0.36
    ونکي
    0.36
    POSITIVE LOGITS
    lectoral
    0.37
    趴
    0.36
     запас
    0.35
     چار
    0.35
    捕捉
    0.34
    錠
    0.34
     নিয়ে
    0.33
     Mee
    0.33
     D
    0.33
     clip
    0.33
    Activations Density 0.000%

    No Known Activations