© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 13757
    Prev
    Next
    INDEX
    Explanations

    startled and scared

    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
    Hydrogen
    0.45
     Tyrol
    0.45
     comandante
    0.44
     eine
    0.44
     eins
    0.43
    legung
    0.43
    蓉
    0.43
     Arya
    0.43
     SMEs
    0.43
     Cables
    0.42
    POSITIVE LOGITS
     пти
    0.57
    雉
    0.57
     게임
    0.52
     startled
    0.52
    🐤
    0.50
    꿩
    0.50
    кмекер
    0.49
     নিবন্ধ
    0.49
     burung
    0.49
     neuropsych
    0.48
    Activations Density 0.032%

    No Known Activations