© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208675
    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
     या
    0.43
     погру
    0.43
    や
    0.43
    ⏰
    0.42
    症
    0.41
     WHEN
    0.41
     thúc
    0.41
    🌧
    0.41
     khi
    0.41
    <h3>
    0.40
    POSITIVE LOGITS
    ".
    0.44
    垡
    0.43
    kun
    0.42
    лардын
    0.42
    Hun
    0.42
    釦
    0.42
     interdependence
    0.42
    кан
    0.41
    castellan
    0.41
    interests
    0.41
    Activations Density 0.000%

    No Known Activations