© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 244820
    Prev
    Next
    INDEX
    Explanations

    code annotations and file paths

    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_40_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
     Eight
    0.50
    8
    0.50
    
    0.47
     Eighth
    0.46
    ⁸
    0.45
     eight
    0.44
     Eighty
    0.43
    auto
    0.42
    ৮
    0.41
    <0xB9>
    0.39
    POSITIVE LOGITS
     филосо
    0.39
    맵
    0.38
     حلقات
    0.38
     அச்ச
    0.36
    Frames
    0.35
     क्रांतिकार
    0.34
     जात
    0.34
     Helpers
    0.34
     น้อย
    0.33
    협
    0.33
    Activations Density 0.034%

    No Known Activations