© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 92633
    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_11_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
    İN
    0.55
    Hab
    0.54
    Fach
    0.51
    Q
    0.50
    Easter
    0.50
    Bag
    0.49
    Evet
    0.49
    Life
    0.48
    Hv
    0.48
    Ꮼ
    0.47
    POSITIVE LOGITS
    render
    0.46
    make
    0.44
     avaliar
    0.43
    \,\
    0.42
    layered
    0.42
    តម្លៃ
    0.42
    ondo
    0.42
     ellipse
    0.42
     alpine
    0.42
     Axe
    0.42
    Activations Density 0.000%

    No Known Activations