© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38358
    Prev
    Next
    INDEX
    Explanations

    case report diagrams

    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_3_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
    t
    0.95
     are
    0.72
     It
    0.67
    sa
    0.66
    िंग
    0.66
    ut
    0.64
    {
    0.62
    त
    0.61
    ے
    0.61
    ের
    0.61
    POSITIVE LOGITS
    ва
    0.69
    ak
    0.65
     früh
    0.64
    Más
    0.64
    an
    0.63
    的名
    0.62
     этому
    0.62
     más
    0.61
    ft
    0.61
    К
    0.61
    Activations Density 0.020%

    No Known Activations