© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 138857
    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_46_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
    rž
    0.37
     percentage
    0.36
    ޭ
    0.36
     challenges
    0.36
     goals
    0.36
    ších
    0.35
    omé
    0.34
     ख़
    0.34
     brighten
    0.34
     te
    0.33
    POSITIVE LOGITS
     ganhar
    0.41
    AdapterView
    0.41
    BRAND
    0.39
     Tuning
    0.38
    Brand
    0.37
    疑
    0.37
     получила
    0.37
    ANTI
    0.36
    ブランド
    0.36
    ਜੀ
    0.36
    Activations Density 0.000%

    No Known Activations