© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 156840
    Prev
    Next
    INDEX
    Explanations

    lies nearby or in

    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_2_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
    ри
    2.05
    are
    1.57
    ul
    1.47
    ri
    1.45
    ка
    1.40
    ру
    1.39
    ু
    1.37
    ك
    1.36
    ו
    1.35
    리
    1.33
    POSITIVE LOGITS
     neem
    0.99
     sådan
    0.99
     have
    0.95
     druk
    0.93
     seres
    0.92
    átu
    0.90
     manifestazione
    0.90
     hanno
    0.89
    夼
    0.88
     střed
    0.88
    Activations Density 0.002%

    No Known Activations