© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 207306
    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_56_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
    ://
    0.44
    ʈ
    0.41
     Carpet
    0.41
    ibili
    0.38
     Reinhold
    0.38
    TextStyle
    0.37
    Pieces
    0.37
     بکر
    0.37
    ৌজ
    0.36
     Blak
    0.36
    POSITIVE LOGITS
     one
    0.88
    一
    0.78
    One
    0.68
     하나
    0.65
    one
    0.65
     One
    0.64
    หนึ่ง
    0.62
     одну
    0.62
     ONE
    0.58
    ONE
    0.58
    Activations Density 0.000%

    No Known Activations