© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35342
    Prev
    Next
    INDEX
    Explanations

    subscribe

    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_11_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
    0.66
    ्तार
    0.66
    سات
    0.64
    يك
    0.63
    沙发
    0.62
    дек
    0.62
    قان
    0.62
    嵐
    0.61
    ಿಗಳು
    0.61
    ্সা
    0.60
    POSITIVE LOGITS
    ey
    0.65
     You
    0.63
    l
    0.61
     lineal
    0.60
    ard
    0.59
     do
    0.58
    ch
    0.57
     It
    0.55
     freeze
    0.55
     Do
    0.54
    Activations Density 0.004%

    No Known Activations