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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 165466
    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_13_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
    ig
    0.64
    at
    0.61
    IO
    0.61
    ER
    0.58
    Sub
    0.58
    SD
    0.57
    LA
    0.57
    :
    0.56
    id
    0.54
    SN
    0.54
    POSITIVE LOGITS
     problèmes
    0.58
     attach
    0.55
     débat
    0.52
     défis
    0.52
     problémy
    0.50
    ક્ત
    0.50
     cleanse
    0.50
    湁
    0.48
     ш
    0.48
     répondre
    0.48
    Activations Density 0.000%

    No Known Activations