© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 211728
    Prev
    Next
    INDEX
    Explanations

    alex

    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_5_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
     to
    1.35
    er
    1.34
    el
    1.31
    ור
    1.15
    ként
    1.15
    '
    1.13
    ル
    1.08
    k
    1.06
    ed
    1.05
    köy
    1.05
    POSITIVE LOGITS
     I
    1.43
    0
    1.12
    ف
    0.98
    י
    0.98
    ي
    0.93
    ม
    0.93
    ੁ
    0.93
     énorme
    0.89
    лся
    0.88
    ö
    0.86
    Activations Density 0.001%

    No Known Activations