© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222144
    Prev
    Next
    INDEX
    Explanations

    même si / mesmo quando

    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_10_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
    ↵
    0.78
    B
    0.72
    на
    0.70
    zinho
    0.68
    D
    0.66
    ated
    0.65
    bed
    0.64
     చేశారు
    0.63
    ation
    0.63
    ings
    0.63
    POSITIVE LOGITS
    ن
    0.99
    ä
    0.87
    é
    0.83
    น
    0.81
    nT
    0.80
    ור
    0.79
    ল
    0.79
    nX
    0.78
    ן
    0.77
     ACH
    0.77
    Activations Density 0.001%

    No Known Activations