© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 46774
    Prev
    Next
    INDEX
    Explanations

    byte array handling

    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
    O
    0.76
    0
    0.65
     jsou
    0.63
    存储
    0.63
    无奈
    0.63
     fallacy
    0.62
    E
    0.60
    、
    0.59
    ترنت
    0.59
    电子商务
    0.59
    POSITIVE LOGITS
    o
    0.75
     Ад
    0.73
     Автор
    0.73
    ப்
    0.70
    nq
    0.69
    𝗔
    0.66
    ną
    0.65
     맨
    0.65
    idP
    0.64
     Б
    0.64
    Activations Density 0.003%

    No Known Activations