© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35324
    Prev
    Next
    INDEX
    Explanations

    Hirschsprung disease and words ending in -ung/-ling

    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
    1
    1.02
    ä
    0.92
    ing
    0.82
    era
    0.80
    f
    0.79
    '
    0.77
    ë
    0.76
    led
    0.75
    ize
    0.75
    ah
    0.72
    POSITIVE LOGITS
     for
    0.78
     combate
    0.73
    كار
    0.73
     voet
    0.71
    ාවිත
    0.69
     notificación
    0.69
    ك
    0.69
     buildFor
    0.68
     abond
    0.68
     موسي
    0.68
    Activations Density 0.001%

    No Known Activations