© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 101846
    Prev
    Next
    INDEX
    Explanations

    shell commands and examples

    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_16_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
    國
    0.46
    비스
    0.45
     world
    0.45
    study
    0.45
    max
    0.44
    Σ
    0.44
    sand
    0.42
     transnational
    0.42
    <
    0.42
    europe
    0.41
    POSITIVE LOGITS
     alba
    0.55
     Patria
    0.54
     wreaths
    0.50
     Patna
    0.49
     juf
    0.48
     Ríos
    0.48
     เพื่อน
    0.48
     Па
    0.48
     Samp
    0.48
    OutputStream
    0.47
    Activations Density 0.051%

    No Known Activations