© 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. 81371
    Prev
    Next
    INDEX
    Explanations

    structured data delimiters

    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
    .
    1.88
    。
    1.55
    LER
    1.35
    го
    1.32
    ра
    1.30
    fte
    1.23
    λ
    1.16
    د
    1.14
    ।
    1.12
     Einf
    1.03
    POSITIVE LOGITS
    の
    1.74
     and
    1.70
    의
    1.64
    ال
    1.52
    は
    1.47
     was
    1.42
    ली
    1.40
     políticas
    1.39
    る
    1.38
    1
    1.38
    Activations Density 0.000%

    No Known Activations