© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195502
    Prev
    Next
    INDEX
    Explanations

    connect you with resources

    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_26_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
    ’
    0.34
     أو
    0.34
     либо
    0.34
    或是
    0.33
    或
    0.33
    リモ
    0.32
    द
    0.32
    International
    0.32
    SSH
    0.32
    ть
    0.31
    POSITIVE LOGITS
     drifts
    0.40
     drifting
    0.40
    
    0.38
     cheerful
    0.35
     nause
    0.34
     সময়ের
    0.34
     struggles
    0.34
     decaying
    0.34
     waking
    0.34
     McKee
    0.34
    Activations Density 0.008%

    No Known Activations