© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 39656
    Prev
    Next
    INDEX
    Explanations

    say "**"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
    …?
    0.40
    ...?
    0.39
     Ultimately
    0.37
     á
    0.37
     வீட்ட
    0.37
     пони
    0.37
     Essentially
    0.36
     Ryanair
    0.35
    <0xC2>
    0.35
    बर्ट
    0.35
    POSITIVE LOGITS
    бак
    0.43
    пати
    0.40
    যাপন
    0.39
    ustin
    0.38
     aimé
    0.37
    elaide
    0.36
     trays
    0.36
     டன்
    0.34
    aton
    0.34
     shave
    0.34
    Activations Density 0.008%

    No Known Activations