© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15723
    Prev
    Next
    INDEX
    Explanations

    military formation descriptions

    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_40_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
    สต
    0.41
    emat
    0.39
    ឹម
    0.38
    융
    0.38
     pédagog
    0.38
    胛
    0.38
     andDevice
    0.36
    galax
    0.36
     paleo
    0.36
     кафед
    0.36
    POSITIVE LOGITS
     abreast
    0.48
    烬
    0.43
     desple
    0.43
     order
    0.40
     вперед
    0.39
     déploy
    0.39
     avanzar
    0.39
     up
    0.38
    Interval
    0.38
     அப
    0.38
    Activations Density 0.058%

    No Known Activations