© 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. 90389
    Prev
    Next
    INDEX
    Explanations

    local pathways and Nasser

    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
    蔣
    0.64
     politič
    0.62
    voren
    0.60
    ен
    0.59
    発生
    0.58
    мо
    0.57
    ສ່ວນ
    0.57
     Neolithic
    0.57
    ᶰ
    0.57
     Boch
    0.57
    POSITIVE LOGITS
    ু
    0.68
     uppercase
    0.65
    i
    0.65
    orse
    0.64
    ra
    0.63
     cues
    0.61
     deductions
    0.61
     mengen
    0.58
    prüsü
    0.57
    lecting
    0.57
    Activations Density 0.000%

    No Known Activations