© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16150
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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_34_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
     kebak
    0.41
    INEN
    0.40
    সিস
    0.40
    曷
    0.40
    луу
    0.40
     احترام
    0.39
    ItemLayout
    0.39
     इंडोनेशिया
    0.39
    ülő
    0.39
     مشکل
    0.38
    POSITIVE LOGITS
     eff
    0.38
    笵
    0.37
     F
    0.37
     fer
    0.37
    ण्डी
    0.37
     grew
    0.36
    gradient
    0.36
     Fl
    0.36
    came
    0.35
    sp
    0.35
    Activations Density 0.001%

    No Known Activations