© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 63023
    Prev
    Next
    INDEX
    Explanations

    kind or kinder

    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_59_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
    stringstream
    0.35
    pre
    0.34
    afat
    0.34
    チャンス
    0.33
    uden
    0.33
     ያለው
    0.33
    📲
    0.33
    ضاع
    0.32
    杆
    0.32
     besteht
    0.32
    POSITIVE LOGITS
     kind
    1.08
    Kind
    1.08
     Kind
    1.06
     KIND
    1.05
    kind
    1.00
     kinder
    0.86
     Kinder
    0.79
    Kinder
    0.73
    KIN
    0.72
    kinder
    0.72
    Activations Density 0.000%

    No Known Activations