© 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. 35836
    Prev
    Next
    INDEX
    Explanations

    conversational AI responses

    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
    convolve
    0.45
     must
    0.42
    must
    0.40
    이렇게
    0.38
    蕌
    0.36
    㧿
    0.36
    MUST
    0.36
    Must
    0.35
    CI
    0.35
    thus
    0.35
    POSITIVE LOGITS
    蛆
    0.39
     оз
    0.38
     می‌باشد
    0.38
    imental
    0.36
    ื่อน
    0.36
    啞
    0.36
    一把
    0.35
     responsabilità
    0.35
     এইচডি
    0.35
    শ্বরের
    0.35
    Activations Density 0.134%

    No Known Activations