© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 51457
    Prev
    Next
    INDEX
    Explanations

    for

    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_55_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
     Pounds
    0.42
     +-
    0.41
     '@
    0.41
     dias
    0.39
     kilograms
    0.39
     '[
    0.38
     Tre
    0.38
     th
    0.38
    ▮
    0.38
     days
    0.37
    POSITIVE LOGITS
    Corruption
    0.39
    Directions
    0.38
     وقال
    0.37
    directions
    0.37
    Structure
    0.36
    zur
    0.36
    КП
    0.36
     synergy
    0.35
    赦
    0.35
    comand
    0.35
    Activations Density 0.005%

    No Known Activations