© 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. 3822
    Prev
    Next
    INDEX
    Explanations

    CI/CD, CircleCI, KeePass, binomial, Travis CI

    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
    WhatsApp
    0.42
    рида
    0.41
    LinkedIn
    0.38
    ดิ
    0.38
     व्हाट
    0.38
    Actors
    0.37
     仮
    0.37
    Facebook
    0.36
    仮
    0.36
    פס
    0.36
    POSITIVE LOGITS
     Travis
    0.67
    Travis
    0.66
    travis
    0.63
     tra
    0.60
     Tra
    0.50
    Trait
    0.47
     token
    0.46
     тра
    0.45
    Tra
    0.45
    ether
    0.44
    Activations Density 0.084%

    No Known Activations