© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 60378
    Prev
    Next
    INDEX
    Explanations

    prisms

    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_11_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
     vorbere
    0.52
    }-\
    0.50
    セス
    0.48
     Kone
    0.47
    篮球
    0.47
     Spani
    0.47
    సో
    0.46
     substantiated
    0.46
     hemispheres
    0.46
    j
    0.46
    POSITIVE LOGITS
     능력
    0.59
     แต่
    0.54
     but
    0.50
     شاید
    0.50
     pasar
    0.50
     tujuan
    0.50
    ked
    0.49
     då
    0.49
    ånd
    0.49
    getDay
    0.48
    Activations Density 0.000%

    No Known Activations