© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40375
    Prev
    Next
    INDEX
    Explanations

    food ingredients and recipes

    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_11_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
    它
    0.70
    ת
    0.64
    т
    0.62
    יות
    0.59
    ية
    0.59
    집합
    0.58
    机
    0.58
    ತ
    0.57
    त
    0.55
     представи
    0.55
    POSITIVE LOGITS
    0
    0.88
    4
    0.85
    5
    0.74
    3
    0.72
    2
    0.68
     चार
    0.60
    fk
    0.60
    Four
    0.59
    7
    0.59
     +(
    0.58
    Activations Density 0.004%

    No Known Activations