© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 40675
    Prev
    Next
    INDEX
    Explanations

    sternly speaking

    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
    т
    0.67
    ת
    0.67
     abound
    0.66
    ем
    0.64
    사
    0.64
    ение
    0.62
     refute
    0.61
    プ
    0.60
    он
    0.60
    يار
    0.60
    POSITIVE LOGITS
     HJ
    0.72
    ten
    0.71
    rien
    0.71
     Creative
    0.68
    ino
    0.67
     Одна
    0.64
     Recognition
    0.64
    ja
    0.64
    fd
    0.64
     Collaborative
    0.63
    Activations Density 0.001%

    No Known Activations