© 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. 43910
    Prev
    Next
    INDEX
    Explanations

    short selling or short position

    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
     ist
    0.23
    カーテン
    0.22
     enjoys
    0.22
     welds
    0.22
     maintains
    0.21
     Maintains
    0.21
     Ե
    0.20
     detects
    0.20
     tweeted
    0.20
    isteren
    0.20
    POSITIVE LOGITS
    convers
    0.21
    ções
    0.21
    Winter
    0.21
    vā
    0.21
    t
    0.21
    và
    0.21
    Locale
    0.20
    Algun
    0.20
    ти
    0.20
     localidad
    0.20
    Activations Density 0.003%

    No Known Activations