© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 116368
    Prev
    Next
    INDEX
    Explanations

    exploring the fabric of reality

    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_27_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
    ='.$
    0.40
     Easier
    0.38
     Scientist
    0.38
    JOptionPane
    0.38
     stagn
    0.36
     Attributes
    0.36
    壓縮
    0.35
    oches
    0.35
     Apre
    0.34
     Biosciences
    0.34
    POSITIVE LOGITS
    حول
    0.41
    បទ
    0.41
    ┎
    0.40
     parchment
    0.38
     oko
    0.38
    ندن
    0.38
     gulp
    0.38
    永
    0.36
     Parch
    0.36
     koş
    0.36
    Activations Density 0.000%

    No Known Activations