© 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. 122341
    Prev
    Next
    INDEX
    Explanations

    Potsdam, dark fantasy, Byrne

    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
    1.59
    l
    1.27
    r
    1.23
    (
    0.91
    A
    0.88
    k
    0.87
    c
    0.85
    g
    0.80
    h
    0.78
    v
    0.77
    POSITIVE LOGITS
    0.80
     for
    0.75
     può
    0.75
     önce
    0.72
     contrôler
    0.71
     në
    0.71
     puedo
    0.71
     güneş
    0.70
     equilibrio
    0.70
     peux
    0.70
    Activations Density 0.000%

    No Known Activations