© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 144320
    Prev
    Next
    INDEX
    Explanations

    HelloWorld, SUSY, HashTable, Ningbo

    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_0_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
    ت
    2.20
    ла
    1.93
    ية
    1.72
    ール
    1.66
    т
    1.53
    л
    1.50
    as
    1.45
    at
    1.44
    ad
    1.36
    lar
    1.34
    POSITIVE LOGITS
    s
    1.86
    re
    1.31
    sin
    1.26
    ﺍ
    1.18
    top
    1.17
     notific
    1.16
    test
    1.15
    n
    1.14
    r
    1.10
    PO
    1.09
    Activations Density 0.000%

    No Known Activations