© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 119447
    Prev
    Next
    INDEX
    Explanations

    code structure punctuation

    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_38_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
     flush
    0.38
    Linki
    0.38
     showAlert
    0.37
    컬
    0.37
     branch
    0.36
    Smoothing
    0.36
    зина
    0.36
    সৌ
    0.36
    bro
    0.36
    Shiv
    0.36
    POSITIVE LOGITS
    韵
    0.43
    arbeiter
    0.38
     ডোজ
    0.37
    docs
    0.37
    経過
    0.36
    潼
    0.36
     நீரில்
    0.35
    Roses
    0.35
    läge
    0.35
    рит
    0.35
    Activations Density 0.001%

    No Known Activations