© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28633
    Prev
    Next
    INDEX
    Explanations

    beans, peas, legumes, sprouts

    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_10_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
    t
    0.44
    ל
    0.40
        
    0.40
    e
    0.40
     death
    0.39
     यदि
    0.38
    不过
    0.38
    わからない
    0.38
    دی
    0.37
    Death
    0.37
    POSITIVE LOGITS
     beans
    0.39
     chickpeas
    0.38
     ℝ
    0.38
     Peas
    0.36
    \
    0.36
     peas
    0.35
    ória
    0.34
    peas
    0.34
     Beans
    0.33
     흐
    0.33
    Activations Density 0.027%

    No Known Activations