© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 133995
    Prev
    Next
    INDEX
    Explanations

    corpus, corvus, corneal, coroutines, corrosion, coroplast, corundum, corridor

    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_1_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
    r
    1.90
    l
    1.84
    i
    1.76
    n
    1.65
    a
    1.59
    u
    1.55
    y
    1.51
    k
    1.50
    is
    1.49
    the
    1.45
    POSITIVE LOGITS
    HttpSession
    0.94
    .
    0.91
    いますが
    0.86
    .​
    0.83
    ..");
    0.83
    ቒ
    0.82
     vicar
    0.80
    .');
    0.77
     koleg
    0.77
     불구
    0.77
    Activations Density 0.001%

    No Known Activations