© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158377
    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
    고
    1.46
     acol
    1.30
    ে
    1.28
     inclin
    1.27
    ש
    1.27
    י
    1.26
     apoi
    1.24
    দ
    1.20
     orn
    1.17
     antics
    1.17
    POSITIVE LOGITS
    an
    1.34
    ale
    1.19
    ing
    1.11
    of
    1.08
    ان
    1.08
    id
    1.05
    eld
    1.04
    ul
    1.03
    Y
    1.03
    ast
    1.02
    Activations Density 0.000%

    No Known Activations