© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 196056
    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_26_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
    attempts
    0.55
     attempts
    0.46
    াং
    0.45
     책임
    0.44
    রাজনৈতিক
    0.44
     gubit
    0.43
     吃
    0.42
    amsu
    0.42
    عال
    0.42
    ENABLED
    0.41
    POSITIVE LOGITS
    ní
    0.40
     language
    0.40
    liği
    0.40
    ist
    0.40
    _
    0.40
    tr
    0.40
    сті
    0.40
     dictionary
    0.39
    style
    0.39
     eden
    0.39
    Activations Density 0.000%

    No Known Activations