© 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. 76767
    Prev
    Next
    INDEX
    Explanations

    introductions / welcome statements

    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
     initializes
    0.40
     pres
    0.38
    ꯤ
    0.38
     resaltar
    0.37
    Reasoner
    0.37
     шля
    0.36
     Pres
    0.36
    лось
    0.35
    ଥ
    0.35
     получилось
    0.35
    POSITIVE LOGITS
    You
    0.38
     ডেভেলপ
    0.37
    Dear
    0.37
     واحده
    0.36
    you
    0.36
    丏
    0.35
    閱
    0.35
    but
    0.34
     나
    0.34
    And
    0.34
    Activations Density 0.001%

    No Known Activations