© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 204307
    Prev
    Next
    INDEX
    Explanations

    intermediate

    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_6_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
    在
    1.02
     as
    0.93
    的
    0.93
    a
    0.88
     aswell
    0.86
    và
    0.86
    Name
    0.85
    v
    0.83
    EN
    0.80
    se
    0.79
    POSITIVE LOGITS
     смесь
    0.96
    ە
    0.91
     medicamento
    0.91
    ０
    0.90
    ி
    0.89
    iiv
    0.88
    ле
    0.87
    ി
    0.87
     учреждений
    0.86
     продуктов
    0.86
    Activations Density 0.000%

    No Known Activations