© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59594
    Prev
    Next
    INDEX
    Explanations

    anagrams

    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_2_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
    ى
    1.09
    f
    0.90
    <0x80>
    0.88
    هِ
    0.72
    ек
    0.71
    ре
    0.70
    h
    0.70
    ன்
    0.68
    ю
    0.68
    ر
    0.67
    POSITIVE LOGITS
     is
    0.92
     a
    0.75
    EM
    0.70
     contenuti
    0.70
     ও
    0.69
     la
    0.68
     historian
    0.67
     y
    0.66
     strategi
    0.66
     et
    0.66
    Activations Density 0.000%

    No Known Activations