© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167194
    Prev
    Next
    INDEX
    Explanations

    [0], [1]

    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
     だ
    0.36
    もお
    0.36
    和大
    0.36
     Dar
    0.35
     Careful
    0.35
    ippy
    0.35
     шаг
    0.35
     Agra
    0.35
    oughs
    0.35
     Tabor
    0.35
    POSITIVE LOGITS
     handlebar
    0.39
     unités
    0.37
     სას
    0.37
    numero
    0.35
    镭
    0.35
    ܚ
    0.35
     necks
    0.35
     един
    0.34
    plural
    0.34
    curso
    0.33
    Activations Density 0.133%

    No Known Activations