© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 8313
    Prev
    Next
    INDEX
    Explanations

    security risks measures mechanisms warnings

    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
     nhánh
    0.37
     ধার
    0.37
    mailed
    0.37
    addington
    0.37
     عدم
    0.36
    攜
    0.36
    attham
    0.36
     fake
    0.36
     स्टैट
    0.36
    ()[
    0.35
    POSITIVE LOGITS
    nen
    0.37
    Certificate
    0.37
    sect
    0.35
    model
    0.34
     Circus
    0.34
     Doremi
    0.34
    义务
    0.34
    시
    0.34
    Seconds
    0.33
     strikes
    0.33
    Activations Density 0.047%

    No Known Activations