© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 234063
    Prev
    Next
    INDEX
    Explanations

    depends on / determined by

    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_32_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
     callSettings
    0.41
    verw
    0.38
    xcodep
    0.38
    事實
    0.37
    ショー
    0.37
    𝖔
    0.37
     खुलकर
    0.36
     accomp
    0.35
    Oku
    0.35
    耋
    0.35
    POSITIVE LOGITS
     मूवमेंट
    0.37
     ids
    0.36
     Ritual
    0.36
    મ્પ
    0.36
    ids
    0.35
    ুদ্ধে
    0.35
     Lincoln
    0.35
    ीण
    0.35
     Forrest
    0.35
     Univers
    0.35
    Activations Density 0.005%

    No Known Activations