© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211338
    Prev
    Next
    INDEX
    Explanations

    calculus

    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_20_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
    षा
    0.49
     मौ
    0.47
     Bobby
    0.46
     mereka
    0.45
     సు
    0.45
    sean
    0.45
    ទេស
    0.44
    沮
    0.44
     मु
    0.43
     Worry
    0.43
    POSITIVE LOGITS
    Classical
    0.44
     accidentally
    0.41
     crunch
    0.41
    không
    0.41
     pile
    0.40
     някои
    0.40
     withstand
    0.39
     trajectory
    0.39
    жнарод
    0.39
    edizione
    0.39
    Activations Density 0.001%

    No Known Activations