© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 5719
    Prev
    Next
    INDEX
    Explanations

    placed in

    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_39_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
    داء
    0.45
     finalList
    0.42
    日閲覧
    0.41
    成绩
    0.40
     createImage
    0.40
    咩
    0.40
     -->'
    0.39
     истории
    0.38
    :'',
    0.38
     ہوئے
    0.38
    POSITIVE LOGITS
    bool
    0.44
     perpend
    0.40
    設置
    0.40
     cilind
    0.39
    riv
    0.39
    vio
    0.38
     U
    0.38
     zigzag
    0.38
    Ö
    0.38
    ठी
    0.38
    Activations Density 0.005%

    No Known Activations