© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14225
    Prev
    Next
    INDEX
    Explanations

    programming constructs

    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_40_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
    ．
    0.73
    ._
    0.65
    .~
    0.50
    ㆍ
    0.48
    .#
    0.44
    .–
    0.44
    ․
    0.44
    .-
    0.43
    .__
    0.42
    ͘
    0.42
    POSITIVE LOGITS
     resident
    0.37
    म्प
    0.37
    லக
    0.36
    টিত
    0.36
     instrumental
    0.35
     /$
    0.35
     ہے
    0.34
    তেন
    0.34
     residentes
    0.34
    ერი
    0.34
    Activations Density 0.065%

    No Known Activations