© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260474
    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_22_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
     केलेल्या
    0.48
     û
    0.48
    னு
    0.44
     FormData
    0.43
    ’
    0.43
    ogas
    0.42
     heur
    0.42
    RNAs
    0.42
    _^
    0.41
     काफ़ी
    0.41
    POSITIVE LOGITS
    dür
    0.46
     Signature
    0.42
     Discourse
    0.42
     Terrain
    0.42
     Comfort
    0.41
     Distributor
    0.41
     Criterion
    0.41
    ジャパン
    0.40
     Sharp
    0.39
     Fiber
    0.39
    Activations Density 0.000%

    No Known Activations