© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42100
    Prev
    Next
    INDEX
    Explanations

    circuit diagram

    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_3_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
    t
    1.05
    지
    0.82
    m
    0.79
    Circle
    0.74
     operas
    0.72
    라
    0.72
    g
    0.70
     CIRC
    0.69
    circle
    0.68
    지만
    0.68
    POSITIVE LOGITS
    ating
    0.56
    ро
    0.55
    isa
    0.54
    с
    0.54
     ليس
    0.53
    érateur
    0.53
    ас
    0.53
    ње
    0.52
     begged
    0.52
    у
    0.52
    Activations Density 0.001%

    No Known Activations