© 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. 93318
    Prev
    Next
    INDEX
    Explanations

    id: pattern

    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
    за
    0.58
    б
    0.56
    ш
    0.54
    아
    0.54
    5
    0.53
    ि
    0.52
    카
    0.52
     szt
    0.51
    0
    0.51
    {
    0.50
    POSITIVE LOGITS
    n
    0.60
    t
    0.55
     Navier
    0.52
     చాలా
    0.52
     homogen
    0.51
    ton
    0.51
    niveau
    0.51
    u
    0.51
     不同
    0.50
     ដោយ
    0.50
    Activations Density 0.000%

    No Known Activations