© 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. 81577
    Prev
    Next
    INDEX
    Explanations

    decentralization

    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
    v
    1.90
    c
    1.88
    ت
    1.57
    h
    1.50
     as
    1.49
    _
    1.46
    ون
    1.45
    k
    1.45
    ل
    1.44
     on
    1.41
    POSITIVE LOGITS
    ↵
    1.70
    ă
    1.69
    ী
    1.55
    ı
    1.52
     I
    1.43
    liği
    1.24
    ë
    1.23
    ла
    1.19
    한
    1.19
    ない
    1.15
    Activations Density 0.000%

    No Known Activations