© 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. 3901
    Prev
    Next
    INDEX
    Explanations

    words starting with H or h

    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
    턴
    0.39
    包装
    0.37
     anchor
    0.37
    ターン
    0.37
     turner
    0.36
    TURN
    0.36
    firmasi
    0.36
    契
    0.36
    ഖ
    0.35
     наші
    0.35
    POSITIVE LOGITS
     сме
    0.42
     siblings
    0.41
    Sibling
    0.39
    fromJson
    0.38
     Clearance
    0.37
     Saal
    0.37
     اتاق
    0.36
     feuilles
    0.36
     shafts
    0.36
    avement
    0.36
    Activations Density 0.061%

    No Known Activations