© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 102011
    Prev
    Next
    INDEX
    Explanations

    chili powder

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_16_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
    រ
    0.58
    អ្វី
    0.55
    CameraController
    0.54
    Eloquent
    0.52
    hut
    0.52
     heutigen
    0.52
     సిని
    0.52
    Sí
    0.52
    Bollywood
    0.50
    Π
    0.50
    POSITIVE LOGITS
    rimps
    0.44
    이블
    0.40
    ɴ
    0.39
    یده
    0.39
    adf
    0.39
     trembling
    0.39
     stat
    0.38
     broker
    0.38
     glow
    0.38
    닝
    0.38
    Activations Density 0.000%

    No Known Activations