© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 149683
    Prev
    Next
    INDEX
    Explanations

    median age

    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_23_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
     동일
    0.44
     יי
    0.44
     جگ
    0.42
     رفض
    0.42
     直
    0.42
    遨
    0.41
     clearContext
    0.39
    強制
    0.38
     முருக
    0.38
     غير
    0.38
    POSITIVE LOGITS
     arousal
    0.44
     life
    0.41
    ូន
    0.41
     portrayed
    0.39
    гии
    0.37
    ≥
    0.37
    ivariate
    0.36
    phin
    0.36
     lifespan
    0.36
     muzzle
    0.36
    Activations Density 0.000%

    No Known Activations