© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228492
    Prev
    Next
    INDEX
    Explanations

    self and personal

    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
     fø
    0.64
     cảm
    0.64
     உண
    0.62
     ع
    0.60
     Feelings
    0.59
     feelings
    0.59
     kän
    0.59
     감
    0.58
    感
    0.57
     احساس
    0.54
    POSITIVE LOGITS
    Inte
    0.35
    规
    0.35
    linejoin
    0.34
     drap
    0.34
    적
    0.34
     Instant
    0.34
     తాను
    0.34
    гой
    0.34
     beyond
    0.33
     fecal
    0.33
    Activations Density 0.001%

    No Known Activations