© 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. 149446
    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
     недвижимости
    0.62
    axies
    0.55
    नियर
    0.54
    closures
    0.53
    ଙ
    0.53
    eniya
    0.52
    shovel
    0.52
    ran
    0.52
    alloy
    0.52
    сний
    0.52
    POSITIVE LOGITS
     let
    0.47
     namesake
    0.45
     nom
    0.45
    τ
    0.43
     else
    0.43
    最
    0.43
     Widget
    0.42
     ActiveRecord
    0.42
     j
    0.41
     note
    0.41
    Activations Density 0.000%

    No Known Activations