© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53981
    Prev
    Next
    INDEX
    Explanations

    degree requirements

    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_30_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
    MaxPool
    0.36
     Cori
    0.34
    뤼
    0.34
    蘼
    0.34
    Wei
    0.34
    доз
    0.33
    weist
    0.33
     karit
    0.33
     酸
    0.33
     нього
    0.33
    POSITIVE LOGITS
     cuyo
    0.39
    幸运
    0.37
     новой
    0.37
    éma
    0.37
     रिव
    0.36
    кну
    0.36
     cujo
    0.36
    ั้ง
    0.36
     ड्र
    0.35
    имуще
    0.35
    Activations Density 0.000%

    No Known Activations