© 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. 57668
    Prev
    Next
    INDEX
    Explanations

    today links

    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
    VERS
    0.55
    轢
    0.55
    వె
    0.54
    integr
    0.53
    Birthday
    0.50
    Cour
    0.50
    LOUIS
    0.50
    Wil
    0.49
    kikh
    0.48
    bordered
    0.48
    POSITIVE LOGITS
     är
    0.58
     triangulation
    0.57
    ia
    0.54
    ät
    0.53
     lä
    0.53
     piè
    0.52
    í
    0.51
     הוא
    0.50
     mains
    0.49
     unsere
    0.49
    Activations Density 0.000%

    No Known Activations