© 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. 217263
    Prev
    Next
    INDEX
    Explanations

    Xbox 360

    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
    i
    0.58
     evita
    0.57
               
    0.57
    ي
    0.57
    with
    0.56
     với
    0.56
    x
    0.54
    ជាមួយ
    0.53
     with
    0.51
     contro
    0.51
    POSITIVE LOGITS
    সার
    0.56
     ಜನ
    0.50
    ље
    0.49
    omás
    0.49
    姦
    0.49
     homogen
    0.48
    állítás
    0.47
    𝖠
    0.46
     ਲ
    0.46
    vět
    0.46
    Activations Density 0.001%

    No Known Activations