© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 32085
    Prev
    Next
    INDEX
    Explanations

    Naive Bayes

    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
     Snyder
    0.40
     आटे
    0.39
    Elli
    0.38
     Elli
    0.38
    痕
    0.37
    란
    0.36
     सला
    0.36
     प्रश
    0.36
     যেকোন
    0.36
    rette
    0.36
    POSITIVE LOGITS
     đáng
    0.46
     Candidate
    0.42
    Candidate
    0.42
     multidiscipl
    0.40
     ವರ್
    0.39
    Saharan
    0.38
    垡
    0.38
    oulou
    0.37
    いています
    0.37
    Berger
    0.37
    Activations Density 0.001%

    No Known Activations