© 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. 2315
    Prev
    Next
    INDEX
    Explanations

    URLs and tech acronyms

    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
    舅
    0.37
     Tool
    0.36
     diretto
    0.36
     TDC
    0.35
     sphinx
    0.35
     Officer
    0.35
     Mme
    0.35
     Value
    0.34
     Southeastern
    0.34
     ધ
    0.34
    POSITIVE LOGITS
    Digital
    0.43
     डिजिटल
    0.41
     디지털
    0.39
    aime
    0.37
    Rose
    0.37
    digital
    0.37
    rose
    0.36
     Digital
    0.35
    Configure
    0.35
    Microsoft
    0.35
    Activations Density 0.060%

    No Known Activations