© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32488
    Prev
    Next
    INDEX
    Explanations

    Alfred

    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_50_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
     L
    0.52
     m
    0.41
     திர
    0.40
     ম
    0.40
     M
    0.40
     ല
    0.39
     Series
    0.38
     सीरीज
    0.38
     syringes
    0.38
     ம
    0.38
    POSITIVE LOGITS
     Alfred
    0.42
     الف
    0.41
    Void
    0.41
    JN
    0.38
     F
    0.38
    olf
    0.38
    anski
    0.38
     ([]
    0.38
    Reporting
    0.37
    Alfred
    0.37
    Activations Density 0.009%

    No Known Activations