© 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. 201468
    Prev
    Next
    INDEX
    Explanations

    operating margin

    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
     f
    0.52
     e
    0.44
    same
    0.44
     c
    0.44
     обществе
    0.44
    ::
    0.43
     samme
    0.42
    <b>
    0.41
     g
    0.41
     same
    0.41
    POSITIVE LOGITS
    बा
    0.48
    笏
    0.47
    BOOK
    0.47
     মধ্যেও
    0.46
    тена
    0.45
     CONFIG
    0.44
     yellowish
    0.44
     Aron
    0.44
    பாத
    0.43
    кинуло
    0.43
    Activations Density 0.000%

    No Known Activations