© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 140500
    Prev
    Next
    INDEX
    Explanations

    zip ties or wire tracer

    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_12_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
    !
    0.30
    Bin
    0.29
    Neue
    0.28
    pe
    0.28
    ائن
    0.28
    Evil
    0.27
    XX
    0.27
    Burn
    0.26
    Histoire
    0.26
    oc
    0.26
    POSITIVE LOGITS
     Ds
    0.30
     дітей
    0.30
     Ста
    0.29
     детям
    0.29
     До
    0.29
     ד
    0.28
     ді
    0.28
     Опера
    0.28
     Ка
    0.28
     О
    0.28
    Activations Density 0.000%

    No Known Activations