© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 51530
    Prev
    Next
    INDEX
    Explanations

    numbers as float representations

    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_30_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
    صیٰ
    0.47
    zne
    0.39
    焜
    0.39
    punyai
    0.39
    芢
    0.38
    بيت
    0.38
    Conj
    0.38
    Ģ
    0.38
    ục
    0.37
    ücken
    0.37
    POSITIVE LOGITS
     Auss
    0.40
    0.40
     강화
    0.40
     monarchs
    0.40
    resize
    0.39
     pul
    0.39
     fines
    0.38
     worse
    0.38
     charter
    0.38
     Kish
    0.37
    Activations Density 0.000%

    No Known Activations