© 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. 8535
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    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
     pruning
    0.40
     अंध
    0.40
    साईट
    0.37
     ra
    0.37
     ㄱ
    0.37
    ▿
    0.37
     ससुराल
    0.36
    ÿ
    0.35
     dihad
    0.35
     イン
    0.35
    POSITIVE LOGITS
     रिलेटेड
    0.44
    RELATED
    0.37
    ertz
    0.37
    رمین
    0.36
     ಐ
    0.36
     RELATED
    0.35
    एक
    0.35
    שר
    0.35
     testaceis
    0.35
    IgnoreCase
    0.34
    Activations Density 0.027%

    No Known Activations