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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 87278
    Prev
    Next
    INDEX
    Explanations

    self-bot code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_3_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
    (
    0.77
    大
    0.74
    0
    0.72
     to
    0.71
    ărilor
    0.70
    itis
    0.70
    InBackground
    0.68
     glances
    0.68
    ０
    0.67
    ites
    0.64
    POSITIVE LOGITS
    .
    0.91
    ור
    0.89
    ก
    0.80
     humana
    0.75
    ↵
    0.75
     firefighter
    0.72
     royaume
    0.67
    un
    0.66
     keamanan
    0.66
     पूरा
    0.66
    Activations Density 0.001%

    No Known Activations