© 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. 58423
    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
    ری
    1.54
    ها
    1.49
    ren
    1.44
    ss
    1.33
    ре
    1.33
    ุ
    1.32
    ра
    1.28
    𝐬
    1.20
    st
    1.19
    ieres
    1.19
    POSITIVE LOGITS
     by
    1.52
    o
    1.38
    (
    1.30
                  
    1.15
     tienen
    1.13
                 
    1.11
     durch
    1.11
    eil
    1.11
    y
    1.10
    1.07
    Activations Density 0.000%

    No Known Activations