© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43454
    Prev
    Next
    INDEX
    Explanations

    music

    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_13_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
     ادا
    0.62
    ת
    0.58
    الم
    0.53
    ت
    0.53
    ن
    0.52
    ન્ડ
    0.50
     scompar
    0.47
    ेड
    0.47
    elbe
    0.46
    م
    0.45
    POSITIVE LOGITS
     diversión
    0.44
     পাঁচ
    0.44
     туристов
    0.44
    豔
    0.43
     우리는
    0.42
     考え
    0.42
     Sangh
    0.42
     probabilistic
    0.41
     undergraduates
    0.41
     Thirdly
    0.41
    Activations Density 0.009%

    No Known Activations