© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173683
    Prev
    Next
    INDEX
    Explanations

    academic or technical content explanation

    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_20_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
    arraf
    0.23
     LMFBR
    0.22
    ịp
    0.22
    $&$-
    0.22
     mirada
    0.22
    CCOCC
    0.21
     оборудование
    0.21
     CCP
    0.21
     CCR
    0.21
    CCO
    0.20
    POSITIVE LOGITS
    oretically
    0.19
     kurie
    0.18
    चने
    0.18
     halde
    0.18
     दिलेल्या
    0.18
     відста
    0.18
    ጹ
    0.18
     Gen
    0.18
     mislead
    0.18
    克斯
    0.17
    Activations Density 0.000%

    No Known Activations