© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205017
    Prev
    Next
    INDEX
    Explanations

    include

    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_37_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
    gameObjects
    0.45
     الأمير
    0.40
     Amiri
    0.39
    渦
    0.38
    xff
    0.37
     estamp
    0.36
    dbp
    0.36
     реки
    0.35
     Towers
    0.35
    حديد
    0.35
    POSITIVE LOGITS
    phus
    0.39
    詎
    0.38
    的意思
    0.37
    柾
    0.37
    anuts
    0.37
     Cn
    0.37
    സും
    0.36
     nisi
    0.36
    Thats
    0.36
    ORTH
    0.35
    Activations Density 0.001%

    No Known Activations