© 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. 41548
    Prev
    Next
    INDEX
    Explanations

    Chongqing medical

    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
    ي
    1.41
    ت
    1.03
    '
    0.88
    ن
    0.82
    н
    0.77
    i
    0.76
    يل
    0.72
    ه
    0.71
    י
    0.71
    كان
    0.70
    POSITIVE LOGITS
     to
    1.13
     in
    1.01
     the
    0.80
     you
    0.74
     other
    0.71
     industrial
    0.70
     toot
    0.70
     ease
    0.69
     spell
    0.69
     insect
    0.68
    Activations Density 0.001%

    No Known Activations