© 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
    2. Gemma-3-27B-IT
    3. 13-GEMMASCOPE-2-TRANSCODER-262K
    4. 165178
    Prev
    Next
    INDEX
    Explanations

    sentence starters

    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_13_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
     
    0.61
    C
    0.50
    .
    0.44
    N
    0.42
    L
    0.40
     nauc
    0.39
     og
    0.39
     Roux
    0.39
    ,
    0.39
    バ
    0.39
    POSITIVE LOGITS
     Hinduism
    0.54
     सब्जेक्ट
    0.53
     Fonbet
    0.52
     Confucian
    0.52
     gespre
    0.49
     Indians
    0.49
     Tendulkar
    0.48
     பண்ண
    0.48
    Indians
    0.48
     Ettha
    0.47
    Activations Density 0.000%

    No Known Activations