© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51517
    Prev
    Next
    INDEX
    Explanations

    code structure

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_55_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
    OLS
    0.40
     predictors
    0.40
    kapet
    0.39
     استان
    0.38
    ریب
    0.38
     острова
    0.37
    꿍
    0.37
     ै
    0.37
    emetery
    0.36
     HART
    0.36
    POSITIVE LOGITS
     ​​
    0.43
     fragile
    0.38
     Recogn
    0.38
     வழங்க
    0.36
     Ask
    0.36
     {}
    0.36
     il
    0.35
     petit
    0.35
     \*
    0.35
     discouraging
    0.34
    Activations Density 0.008%

    No Known Activations