© 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. 208294
    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
     ¿
    0.63
     ¡
    0.60
     هل
    0.58
    ¿
    0.58
    ¡
    0.47
    هل
    0.45
    Pair
    0.42
     Spacious
    0.40
    है
    0.39
    pairs
    0.38
    POSITIVE LOGITS
     rivol
    0.39
     Decl
    0.39
     করিলে
    0.38
    #############
    0.38
     Noether
    0.38
     በአ
    0.38
    namento
    0.37
    ############
    0.36
    昷
    0.36
     ইহার
    0.35
    Activations Density 0.000%

    No Known Activations