© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154127
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
     Основ
    0.55
    运
    0.53
    鹕
    0.52
    的声音
    0.52
     पेड़
    0.50
     SOUND
    0.50
    调
    0.50
     संयोजन
    0.49
    声音
    0.48
     হস্তান্তর
    0.48
    POSITIVE LOGITS
     fascin
    0.48
     "
    0.47
     daylight
    0.47
     cleanser
    0.46
     fascinating
    0.45
     bakery
    0.45
     fascination
    0.45
     lem
    0.44
     van
    0.44
     relev
    0.43
    Activations Density 0.000%

    No Known Activations