© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3085
    Prev
    Next
    INDEX
    Explanations

    java/kotlin libraries

    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_40_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
    ʸ
    0.41
     Maloney
    0.38
    Folders
    0.38
     Chile
    0.37
    nun
    0.37
    Rest
    0.37
     Fold
    0.37
     automática
    0.37
    ダム
    0.36
     Rest
    0.36
    POSITIVE LOGITS
     allein
    0.39
     আহমদ
    0.38
    瞠
    0.36
    锻
    0.35
     salen
    0.35
    തല
    0.35
    曰
    0.35
     alone
    0.35
    gruppen
    0.35
    ریان
    0.34
    Activations Density 0.001%

    No Known Activations