© 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. 199972
    Prev
    Next
    INDEX
    Explanations

    a

    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
     kal
    0.47
     ка
    0.44
     heavy
    0.43
    Heavy
    0.42
    菲
    0.40
     ká
    0.39
    凤凰
    0.39
     fresh
    0.39
    重
    0.39
    Kathy
    0.38
    POSITIVE LOGITS
     ३
    0.45
     ৪
    0.41
     ૩
    0.40
    ಇ
    0.40
     ৩৬
    0.40
     ۳
    0.40
     छत्तीस
    0.40
     স্র
    0.39
     १३
    0.39
    இ
    0.39
    Activations Density 0.001%

    No Known Activations