© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 200841
    Prev
    Next
    INDEX
    Explanations

    Alan Wake 2

    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_12_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
    fromj
    0.13
    삿
    0.13
     رہتا
    0.13
    𝔱
    0.13
    Logs
    0.13
     ብዙውን
    0.13
    UNO
    0.13
     nCenters
    0.13
     tattha
    0.12
    ▮
    0.12
    POSITIVE LOGITS
     laughable
    0.13
     comforting
    0.12
    ially
    0.12
     chaotic
    0.12
     Así
    0.12
     কার্যকর
    0.11
     हद
    0.11
     gritty
    0.11
     Debido
    0.11
     Corporate
    0.11
    Activations Density 0.000%

    No Known Activations