© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 14-GEMMASCOPE-2-TRANSCODER-262K
    7. 100350
    Prev
    Next
    INDEX
    Explanations

    inventory, mod, elder, move, real

    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_14_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
    妩
    0.13
     まで
    0.13
    חס
    0.13
     Pre
    0.12
     بلو
    0.12
    downcase
    0.12
     Até
    0.12
     romances
    0.12
     até
    0.12
     服
    0.12
    POSITIVE LOGITS
    sor
    0.12
     papillary
    0.12
    tanggal
    0.12
     unplanned
    0.11
    ிருக்கிறது
    0.11
    ैया
    0.11
     toot
    0.11
    arter
    0.11
    거나
    0.11
     unwanted
    0.10
    Activations Density 0.004%

    No Known Activations