© 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. 260793
    Prev
    Next
    INDEX
    Explanations

    sh words

    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
     It
    1.56
    .
    1.35
    ו
    1.23
     νέα
    1.20
     it
    1.19
     You
    1.19
    It
    1.16
     for
    1.15
    č
    1.09
    1
    1.08
    POSITIVE LOGITS
    to
    1.34
    ند
    1.27
    то
    1.24
    ра
    1.20
    на
    1.18
    تي
    1.16
    ти
    1.12
    тися
    1.09
    мо
    1.08
    تا
    1.05
    Activations Density 0.006%

    No Known Activations