© 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. 11527
    Prev
    Next
    INDEX
    Explanations

    electron

    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
     Quelles
    0.29
     Quais
    0.28
     Polícia
    0.27
    ヨーロッパ
    0.27
    嫚
    0.27
     lunghezza
    0.26
     Baal
    0.26
     Tabor
    0.25
     copii
    0.25
    apanicola
    0.25
    POSITIVE LOGITS
    ujen
    0.27
    تيجة
    0.27
    po
    0.25
    ),
    0.25
    ne
    0.25
    r
    0.25
    la
    0.25
    acting
    0.25
    skilled
    0.25
    id
    0.24
    Activations Density 0.016%

    No Known Activations