© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 139766
    Prev
    Next
    INDEX
    Explanations

    coffee

    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_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
    зора
    0.40
    ников
    0.38
     সোন
    0.37
     instructor
    0.37
     اخت
    0.36
    soaked
    0.35
    assar
    0.35
     つ
    0.34
     антен
    0.34
    ੌਰ
    0.34
    POSITIVE LOGITS
     Group
    0.42
     empathy
    0.40
    merce
    0.40
     COT
    0.39
     Robert
    0.39
     quilting
    0.39
     retirement
    0.39
     Tata
    0.39
     Retirement
    0.39
     Santé
    0.38
    Activations Density 0.000%

    No Known Activations