© 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. 199972
    Prev
    Next
    INDEX
    Explanations

    CPM and PERT method analysis

    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
    同步
    0.63
     евре
    0.62
     synchronize
    0.57
     Vegas
    0.55
    ﺱ
    0.55
     Nvidia
    0.55
     nourish
    0.55
     синх
    0.54
     Zebra
    0.54
    微微
    0.54
    POSITIVE LOGITS
    scription
    0.56
    idimensional
    0.54
    order
    0.53
    enemies
    0.53
    );
    0.52
    aciones
    0.52
    comments
    0.52
    ship
    0.51
    descriptions
    0.51
    idirectional
    0.51
    Activations Density 0.002%

    No Known Activations