© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 163620
    Prev
    Next
    INDEX
    Explanations

    by

    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_31_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
     quotidien
    0.29
     conjuntos
    0.28
     পুনরায়
    0.27
    vertine
    0.27
    नल
    0.26
    ₪
    0.26
     khăn
    0.26
    乓
    0.26
    水源
    0.26
     گلوکار
    0.26
    POSITIVE LOGITS
     jogging
    0.30
    toned
    0.29
    მო
    0.29
    কর্ণ
    0.29
    Elev
    0.28
     Ment
    0.28
     Elev
    0.28
     Rest
    0.28
     वर्क
    0.28
    ഹമ്മ
    0.27
    Activations Density 0.000%

    No Known Activations