© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195113
    Prev
    Next
    INDEX
    Explanations

    code declarations

    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_27_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
     S
    0.44
     und
    0.44
     V
    0.42
     Jay
    0.40
    dd
    0.39
     Lay
    0.38
     o
    0.37
     O
    0.37
     de
    0.37
     Oder
    0.37
    POSITIVE LOGITS
    skcipher
    0.42
     keySchedule
    0.39
     idioms
    0.38
    xcschemes
    0.38
     类型
    0.38
     encodes
    0.38
    WebKit
    0.37
    ুবাদ
    0.37
    Readable
    0.37
     Великобритании
    0.37
    Activations Density 0.002%

    No Known Activations