© 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. 46453
    Prev
    Next
    INDEX
    Explanations

    romanticism, -ize, -ism, -ent endings

    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
    K
    0.71
    urus
    0.70
    țul
    0.66
    G
    0.66
    ри
    0.65
    NHS
    0.65
    AC
    0.64
    ase
    0.61
    J
    0.61
    V
    0.60
    POSITIVE LOGITS
    t
    1.52
    d
    0.91
    n
    0.80
    a
    0.75
    h
    0.70
    ंना
    0.68
    ند
    0.68
    dim
    0.67
     Giveen
    0.66
     Romantic
    0.66
    Activations Density 0.006%

    No Known Activations