© 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. 29550
    Prev
    Next
    INDEX
    Explanations

    example usage

    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
    }($
    0.29
     LAY
    0.28
     Кла
    0.28
    Jackie
    0.26
     Кі
    0.26
    िके
    0.26
     жы
    0.26
    +$
    0.25
    groupby
    0.25
     شب
    0.25
    POSITIVE LOGITS
     record
    0.35
     Record
    0.34
     रिकॉर्ड
    0.34
     Conjug
    0.31
     Phòng
    0.31
     ansi
    0.30
     Holton
    0.30
     svg
    0.30
     রেকর্ড
    0.29
    record
    0.29
    Activations Density 0.011%

    No Known Activations