© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 161817
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ی
    1.41
    s
    1.17
    ेल
    1.16
     in
    1.15
    ים
    1.15
    ן
    1.13
    ig
    1.02
    ە
    0.98
    ง
    0.96
    є
    0.96
    POSITIVE LOGITS
    it
    1.04
    一
    1.02
    دين
    1.00
    don
    0.99
     выбо
    0.98
     صلى
    0.98
    donut
    0.96
    dba
    0.95
     lím
    0.95
     досто
    0.95
    Activations Density 0.000%

    No Known Activations