© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 240945
    Prev
    Next
    INDEX
    Explanations

    handles edge cases and checks

    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_25_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
     maß
    0.29
    ualitas
    0.26
    saus
    0.26
    _{-
    0.25
    oped
    0.25
    ément
    0.25
    🔍
    0.25
     заказ
    0.25
    onucle
    0.25
     composé
    0.24
    POSITIVE LOGITS
     प्रसन्न
    0.29
     Spending
    0.25
    ახ
    0.25
    воря
    0.25
    JUN
    0.25
     М
    0.25
     కాని
    0.25
     ту
    0.25
    厛
    0.24
     пытается
    0.24
    Activations Density 0.008%

    No Known Activations