© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    4. 48363
    Prev
    Next
    INDEX
    Explanations

    Gary Keller & Jay Papasan list format

    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_10_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
     Silence
    0.50
    oh
    0.49
     Produ
    0.48
    agogues
    0.47
     silence
    0.47
     deputies
    0.46
    igham
    0.43
    د
    0.43
     Ohio
    0.43
     Ethiopian
    0.43
    POSITIVE LOGITS
    เอา
    0.52
    ʂ
    0.50
    FlashValue
    0.50
    Subscribe
    0.49
    这时候
    0.47
    ɭ
    0.47
     взаимодей
    0.47
    ៧
    0.47
     travaille
    0.46
    សារ
    0.46
    Activations Density 0.000%

    No Known Activations