© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 15065
    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_34_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
    伤
    0.39
     სახ
    0.38
    perturbed
    0.37
     dise
    0.36
    क्योंकि
    0.36
    omor
    0.36
    傷
    0.36
     darn
    0.35
    誅
    0.35
     damn
    0.35
    POSITIVE LOGITS
     Presumably
    0.45
     вероятно
    0.44
     احتمال
    0.40
     consacré
    0.39
     बनाम
    0.38
    ཿ
    0.38
    rencies
    0.38
     структуры
    0.38
    🌋
    0.37
     структуру
    0.37
    Activations Density 0.000%

    No Known Activations