© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 201632
    Prev
    Next
    INDEX
    Explanations

    Holy Roman Empire

    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
    .
    1.05
     on
    1.03
    ing
    1.02
    y
    0.87
    ক
    0.87
     categor
    0.78
    e
    0.77
    p
    0.77
    á
    0.76
    6
    0.73
    POSITIVE LOGITS
    lere
    0.81
    dalam
    0.81
    lara
    0.78
    lü
    0.75
    ları
    0.75
    行う
    0.70
    ಬ್ಬಿಣ
    0.70
    lou
    0.70
     wody
    0.70
     സാധ
    0.69
    Activations Density 0.000%

    No Known Activations