© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59808
    Prev
    Next
    INDEX
    Explanations

    interactive charts and interfaces

    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_11_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
     ayatan
    0.70
     Oahu
    0.58
     크라운
    0.58
    ꞌ
    0.57
     Osaka
    0.56
     Bhagavato
    0.55
     Oeste
    0.53
    <unused2135>
    0.53
    ä
    0.52
     Aş
    0.52
    POSITIVE LOGITS
    Color
    0.63
    1
    0.63
    T
    0.62
    Steps
    0.59
    J
    0.57
    A
    0.57
    St
    0.55
    Mir
    0.55
    M
    0.55
    Wiring
    0.54
    Activations Density 0.071%

    No Known Activations