© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3470
    Prev
    Next
    INDEX
    Explanations

    arn:aws: followed by service and resource type

    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_39_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
    खम
    0.38
    钜
    0.38
     قطع
    0.38
     مقرر
    0.37
     ตั้ง
    0.36
     Centuries
    0.36
    hoi
    0.36
    প্রকার
    0.36
    ็ต
    0.35
    เส้น
    0.35
    POSITIVE LOGITS
     nav
    0.39
     join
    0.38
     tre
    0.38
    join
    0.38
     layering
    0.37
    meida
    0.37
    }=-
    0.37
     rosé
    0.36
    erts
    0.36
     pass
    0.36
    Activations Density 0.002%

    No Known Activations