© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11822
    Prev
    Next
    INDEX
    Explanations

    UK, wings, CFL

    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_13_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
     universal
    0.52
     stagger
    0.51
     staggered
    0.47
     reconciled
    0.46
     सूरज
    0.46
     staggering
    0.45
     virtuous
    0.45
    (
    0.45
     kaleidoscopic
    0.44
     jarring
    0.44
    POSITIVE LOGITS
     إ
    0.53
    жала
    0.52
    른
    0.49
    ressa
    0.49
     정치
    0.49
    ﺇ
    0.48
     fisk
    0.48
    س
    0.48
    ﺯ
    0.47
     س
    0.47
    Activations Density 0.027%

    No Known Activations