© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 34633
    Prev
    Next
    INDEX
    Explanations

    blood brain barrier

    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_3_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
    ;
    0.80
    ми
    0.76
    什么
    0.68
    -
    0.66
     tremble
    0.66
    ంలో
    0.64
     ""),
    0.64
    ки
    0.63
    ó
    0.63
    لي
    0.63
    POSITIVE LOGITS
    AN
    0.57
    OR
    0.56
    I
    0.56
    AR
    0.55
    It
    0.55
    臓
    0.55
    げて
    0.54
    ENN
    0.54
     in
    0.53
    Are
    0.53
    Activations Density 0.003%

    No Known Activations