© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201072
    Prev
    Next
    INDEX
    Explanations

    facepalm emoji followed by relatable mistakes

    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_6_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
    ac
    1.23
    <0x80>
    1.13
    ي
    1.08
    ak
    1.03
    <
    0.91
    տ
    0.86
    ে
    0.84
    res
    0.81
    ic
    0.80
    ح
    0.79
    POSITIVE LOGITS
     as
    1.25
    ।
    1.24
    ።
    1.23
    ۔
    1.22
    。
    1.02
    은
    1.01
     is
    0.97
    గా
    0.95
    จะ
    0.95
    ного
    0.94
    Activations Density 0.001%

    No Known Activations