© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214596
    Prev
    Next
    INDEX
    Explanations

    robots EM

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Ost
    0.46
    Ost
    0.41
    asilkan
    0.41
    ("#{
    0.40
    Av
    0.39
     Wars
    0.38
     PDT
    0.38
    Oj
    0.38
     获取
    0.38
     வடக்கு
    0.38
    POSITIVE LOGITS
    ्डा
    0.41
     মূ
    0.40
    ells
    0.40
     els
    0.40
     pull
    0.39
     ско
    0.39
    끌
    0.39
     pursuit
    0.38
    끗
    0.37
    hum
    0.37
    Activations Density 0.031%

    No Known Activations