© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7009
    Prev
    Next
    INDEX
    Explanations

    nn.TransformerEncoderLayer

    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_39_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
    yscanner
    0.42
    盈
    0.42
    リュ
    0.40
     Pads
    0.38
     pads
    0.38
     timescale
    0.38
     একের
    0.38
     hierarchy
    0.37
     hierarchies
    0.37
     ludicrous
    0.37
    POSITIVE LOGITS
    Libs
    0.42
    Bid
    0.40
    边
    0.39
    sym
    0.38
    Sym
    0.38
    zonej
    0.38
    Correlation
    0.38
    bmod
    0.37
    하도록
    0.36
    闗
    0.36
    Activations Density 0.000%

    No Known Activations