© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 86598
    Prev
    Next
    INDEX
    Explanations

    structured prompt

    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_18_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
    ik
    0.57
    elen
    0.56
    odymium
    0.54
    キュー
    0.50
     Verfahren
    0.49
    jalpha
    0.48
    ר
    0.48
    ގ
    0.47
     Lagrangian
    0.47
     Katal
    0.47
    POSITIVE LOGITS
    Cruz
    0.48
    زام
    0.47
     bất
    0.43
    及时
    0.42
    Odds
    0.42
    चने
    0.41
    Horn
    0.40
     ذریع
    0.40
     importantes
    0.40
    ዷ
    0.40
    Activations Density 0.000%

    No Known Activations