© 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. 245495
    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_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
     Ingram
    0.44
     api
    0.44
     send
    0.43
    send
    0.42
    ﹂
    0.41
     mengirim
    0.41
     পাঠানোর
    0.40
     отправ
    0.39
    wasser
    0.39
     API
    0.38
    POSITIVE LOGITS
     prognosis
    0.41
     মতোই
    0.36
    ubble
    0.35
     gait
    0.35
    estell
    0.34
     butch
    0.34
    Govern
    0.34
     jane
    0.33
    훈
    0.33
     gpd
    0.33
    Activations Density 0.002%

    No Known Activations