© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 227306
    Prev
    Next
    INDEX
    Explanations

    alternate between

    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_6_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
     in
    1.32
    h
    1.05
     are
    0.98
     synchron
    0.97
     ib
    0.96
     ito
    0.96
     accur
    0.95
     acumen
    0.95
     d
    0.93
     s
    0.91
    POSITIVE LOGITS
    л
    1.18
    지
    1.11
    ز
    1.08
    ج
    1.02
    기
    0.97
    اء
    0.95
    지가
    0.93
    的名字
    0.93
    り
    0.92
    ли
    0.91
    Activations Density 0.000%

    No Known Activations