© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 245038
    Prev
    Next
    INDEX
    Explanations

    plotly graph objects (`go`) and charts

    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_40_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
    VM
    0.39
     konz
    0.37
     היי
    0.36
    cu
    0.35
    θν
    0.33
    chuk
    0.33
    특
    0.33
    wrapper
    0.33
    ظ
    0.33
    幌
    0.33
    POSITIVE LOGITS
    resonance
    0.43
    geocode
    0.42
     Lanier
    0.42
     Plane
    0.40
     representation
    0.40
     Đi
    0.40
    isRunning
    0.40
     Cnemidophorus
    0.39
    合わせ
    0.39
     Representation
    0.39
    Activations Density 0.001%

    No Known Activations