© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15194
    Prev
    Next
    INDEX
    Explanations

    years or decades after numbers

    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
     Bard
    0.42
     programa
    0.39
    يهم
    0.37
     eterno
    0.36
    obarb
    0.36
    垟
    0.36
     பார
    0.36
     matrimon
    0.35
     фай
    0.35
     സഹ
    0.34
    POSITIVE LOGITS
     `"
    0.36
    stre
    0.34
    적이
    0.34
     ஊற
    0.34
     गलवान
    0.33
    icist
    0.33
     খে
    0.33
    Processes
    0.32
     ಪದ
    0.32
    exposition
    0.32
    Activations Density 0.052%

    No Known Activations