© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6278
    Prev
    Next
    INDEX
    Explanations

    software build versions

    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
    Tm
    0.39
    Twins
    0.36
    Primer
    0.35
    ㎢
    0.34
     Polyester
    0.34
    ಷ
    0.34
    stö
    0.34
    莒
    0.33
     cnt
    0.33
     nö
    0.32
    POSITIVE LOGITS
     build
    2.03
     Build
    1.88
     builds
    1.88
    build
    1.86
    Build
    1.85
     Builds
    1.77
     BUILD
    1.50
    BUILD
    1.42
     buildup
    1.25
     buil
    1.19
    Activations Density 0.153%

    No Known Activations