© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 118710
    Prev
    Next
    INDEX
    Explanations

    translate localized strings

    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_27_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
     станда
    0.43
    嚆
    0.41
     مدار
    0.41
    tanggal
    0.39
    (\|
    0.37
    ட்ப
    0.36
    الح
    0.36
     चलकर
    0.36
    骜
    0.36
     pertama
    0.36
    POSITIVE LOGITS
     مؤثر
    0.40
    NR
    0.38
    weed
    0.38
     lab
    0.38
     citron
    0.37
    เตรียม
    0.37
     stochastic
    0.37
     tyr
    0.37
     affect
    0.36
     cull
    0.36
    Activations Density 0.000%

    No Known Activations