© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149588
    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_23_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
    r
    0.50
     o
    0.50
     a
    0.48
     nic
    0.47
     Ку
    0.47
     diccionario
    0.47
     принцип
    0.46
    dar
    0.44
     прове
    0.43
    dor
    0.43
    POSITIVE LOGITS
    敺
    0.56
    日から
    0.49
    ㎚
    0.49
    ਨੀ
    0.48
    भाष
    0.48
    лося
    0.47
    ंगन
    0.47
     ਤੋਂ
    0.47
    eneuve
    0.47
     株
    0.47
    Activations Density 0.000%

    No Known Activations