© 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. 165313
    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
     Techn
    0.50
    說
    0.48
     gent
    0.46
     king
    0.46
     more
    0.44
    b
    0.44
     referee
    0.44
    人
    0.43
     returning
    0.42
    p
    0.42
    POSITIVE LOGITS
     यूज्ड
    0.59
    <unused715>
    0.54
     वंदे
    0.52
     வளர்
    0.51
    »),
    0.51
    AssetDiscovery
    0.51
    कर्ताओं
    0.49
    💠
    0.49
    »).
    0.48
    <unused729>
    0.48
    Activations Density 0.000%

    No Known Activations