© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 212753
    Prev
    Next
    INDEX
    Explanations

    rat / ratón / ratones

    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_5_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
    ä
    1.32
    س
    1.02
    ag
    0.96
    ip
    0.96
    oc
    0.94
    atik
    0.93
    ang
    0.92
    ON
    0.92
    é
    0.92
    AT
    0.89
    POSITIVE LOGITS
    ك
    1.06
     de
    1.02
     in
    0.96
    і
    0.92
    יי
    0.91
    ει
    0.89
    이면
    0.88
    로
    0.88
    คุณ
    0.88
    ка
    0.87
    Activations Density 0.000%

    No Known Activations