© 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. 116093
    Prev
    Next
    INDEX
    Explanations

    biographies and descriptions of people

    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
    :");
    0.41
     different
    0.41
     RAR
    0.40
     GPs
    0.39
     data
    0.38
     changes
    0.38
    xt
    0.38
     levels
    0.38
     ture
    0.37
     degrees
    0.37
    POSITIVE LOGITS
    曾在
    0.41
    職
    0.41
    黉
    0.40
     билет
    0.40
    CSc
    0.40
    リーズ
    0.40
     हिरासत
    0.40
     قادر
    0.39
     মহারা
    0.39
    BOSTON
    0.39
    Activations Density 0.004%

    No Known Activations