© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 86647
    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
     hauled
    0.41
    tidak
    0.39
    pathetic
    0.38
    duration
    0.37
     nominated
    0.36
     countenance
    0.36
    -//
    0.36
    vred
    0.36
     கிறிஸ்துவின்
    0.36
    យ៉ាង
    0.35
    POSITIVE LOGITS
    文件夹
    0.41
     Asalamualaikum
    0.41
    னே
    0.40
     வாங்க
    0.40
     стоя
    0.40
    ച്ച്
    0.39
    ܩ
    0.39
     Стаўкі
    0.39
     Pran
    0.38
     段
    0.38
    Activations Density 0.000%

    No Known Activations