© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 207342
    Prev
    Next
    INDEX
    Explanations

    shiver down spine

    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
     Bias
    0.43
     quaisquer
    0.40
     っ
    0.40
     Уен
    0.39
     onus
    0.39
     cualquier
    0.39
     bias
    0.38
    étricas
    0.38
    MathML
    0.38
    Use
    0.37
    POSITIVE LOGITS
     વિવિધ
    0.47
    獸
    0.41
     personalization
    0.40
     customization
    0.40
     notifications
    0.39
     cosmetology
    0.38
     curation
    0.37
     oncology
    0.37
    arounds
    0.37
    兽
    0.37
    Activations Density 0.002%

    No Known Activations