© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 36427
    Prev
    Next
    INDEX
    Explanations

    screen, anomalies, reduction, experience, radio, carrier

    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
    ة
    1.01
    ing
    0.83
    í
    0.77
    ü
    0.76
    л
    0.75
    żyw
    0.72
    ш
    0.70
    ς
    0.70
    ong
    0.67
    ître
    0.66
    POSITIVE LOGITS
    0.83
     t
    0.64
    t
    0.63
     katıl
    0.61
     वहां
    0.59
     were
    0.58
     swan
    0.58
     добав
    0.57
     Moth
    0.57
     codon
    0.57
    Activations Density 0.027%

    No Known Activations