© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91709
    Prev
    Next
    INDEX
    Explanations

    configuration commands `<ASN>`

    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_11_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
    tR
    0.38
    t
    0.36
     Nationality
    0.36
    leaving
    0.34
     Agios
    0.34
     ℝ
    0.33
    聃
    0.33
     empath
    0.33
    ИН
    0.32
     общения
    0.32
    POSITIVE LOGITS
     دیگری
    0.37
     אחר
    0.35
    ب
    0.34
     fired
    0.33
     retrieves
    0.32
     விரைவில்
    0.32
    rupted
    0.32
    ुरी
    0.32
     settimana
    0.32
    みました
    0.32
    Activations Density 0.034%

    No Known Activations