© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 17317
    Prev
    Next
    INDEX
    Explanations

    divergence

    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_34_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
    ForgotPassword
    0.39
    abstract
    0.37
     (.
    0.37
    LOGIN
    0.36
     "***
    0.36
    computation
    0.36
    蛍光
    0.36
     Calculation
    0.36
    aphys
    0.36
     range
    0.35
    POSITIVE LOGITS
    形成了
    0.41
     優
    0.40
     Shower
    0.38
    Shower
    0.38
     ধারাবাহিক
    0.37
    ेंशन
    0.37
    parseDouble
    0.37
     décisions
    0.37
     트리플
    0.37
     сериа
    0.36
    Activations Density 0.018%

    No Known Activations