© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6570
    Prev
    Next
    INDEX
    Explanations

    material properties

    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_39_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
     inviol
    0.42
     размеры
    0.39
    的大小
    0.39
    зайн
    0.38
     diseño
    0.38
     ڈیزائن
    0.38
    вающая
    0.38
    勹
    0.37
     வடிவ
    0.36
     शेप
    0.36
    POSITIVE LOGITS
     milling
    0.41
    含
    0.39
     weep
    0.38
     retrieves
    0.38
     imparted
    0.38
     含
    0.38
     binder
    0.36
     rut
    0.36
    齐
    0.36
    ash
    0.35
    Activations Density 0.176%

    No Known Activations