© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132329
    Prev
    Next
    INDEX
    Explanations

    PCTC, PNAS, ECRC, PTSD, eSIM, NCSC, SIM

    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_1_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
    el
    1.55
    н
    1.45
    o
    1.38
    д
    1.33
    ar
    1.30
    a
    1.21
    -
    1.20
    g
    1.20
        
    1.18
    et
    1.18
    POSITIVE LOGITS
     νέ
    1.26
     ομά
    1.20
     считается
    1.17
     ошибок
    1.16
     është
    1.16
    진다
    1.09
     zmiany
    1.09
    ἲ
    1.08
     ہیں۔
    1.05
     аналоги
    1.05
    Activations Density 0.000%

    No Known Activations