© 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. 176726
    Prev
    Next
    INDEX
    Explanations

    peas

    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
    み
    0.50
    హ్
    0.47
    MI
    0.45
    hne
    0.43
    َم
    0.43
    hna
    0.42
    omio
    0.41
    mi
    0.41
    me
    0.41
    Mi
    0.41
    POSITIVE LOGITS
    قية
    0.55
    ގައި
    0.48
     pea
    0.46
     Pea
    0.46
    peas
    0.40
    pea
    0.39
     Kies
    0.39
    豌
    0.39
     fe
    0.38
     kaik
    0.38
    Activations Density 0.004%

    No Known Activations