© 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. 217556
    Prev
    Next
    INDEX
    Explanations

    product/coast/designation/build

    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
    م
    0.46
     esp
    0.45
    可靠
    0.43
     cada
    0.42
    물
    0.42
     dependable
    0.41
    炁
    0.41
     seçim
    0.40
    台中
    0.40
     supernovae
    0.40
    POSITIVE LOGITS
     ต
    0.50
     Russland
    0.46
    andt
    0.46
    emed
    0.45
    rien
    0.45
     उन्हीं
    0.45
     Hadid
    0.43
     PART
    0.43
    pregn
    0.43
     ห
    0.42
    Activations Density 0.000%

    No Known Activations