© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 210366
    Prev
    Next
    INDEX
    Explanations

    mitigations

    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_19_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
     ويع
    0.57
     Because
    0.52
    Ó
    0.51
     وش
    0.48
     Admittedly
    0.48
     annot
    0.48
     because
    0.48
     fue
    0.48
     elig
    0.47
     Improving
    0.47
    POSITIVE LOGITS
    itimate
    0.49
    і
    0.43
    スポーツ
    0.43
    اندی
    0.43
    íqu
    0.42
     ইমরান
    0.41
    ﯽ
    0.41
     গর্
    0.40
    ครอง
    0.40
    ajib
    0.40
    Activations Density 0.000%

    No Known Activations