© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171269
    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_20_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
    乙
    0.48
    㴓
    0.45
    Bedroom
    0.44
    сій
    0.44
    随着
    0.43
     Yath
    0.43
     острова
    0.43
    TimeString
    0.43
    互联网档案馆
    0.42
    ина
    0.42
    POSITIVE LOGITS
    ponse
    0.49
    pond
    0.48
    tbody
    0.48
     consigli
    0.47
    ,
    0.45
     pond
    0.44
     trident
    0.44
     brindar
    0.44
     quarant
    0.42
     flying
    0.42
    Activations Density 0.000%

    No Known Activations