© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 206152
    Prev
    Next
    INDEX
    Explanations

    instructions and questions

    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_25_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
    bär
    0.42
     نظر
    0.40
     bä
    0.39
    Get
    0.38
    特定
    0.38
    Multiplier
    0.38
     фак
    0.38
    =(\
    0.38
    ？
    0.37
    Draw
    0.37
    POSITIVE LOGITS
     murmured
    0.38
     Chromatogr
    0.38
     tinha
    0.38
     Frankenstein
    0.36
     tätig
    0.36
     continued
    0.35
     Trends
    0.35
     funcionamiento
    0.35
     Landscape
    0.35
     Sanders
    0.34
    Activations Density 0.022%

    No Known Activations