© 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. 133739
    Prev
    Next
    INDEX
    Explanations

    what a

    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
    v
    0.92
     người
    0.88
    arında
    0.80
    する
    0.79
     pracę
    0.77
    inė
    0.76
     soorten
    0.75
     année
    0.74
    inį
    0.74
     사람
    0.74
    POSITIVE LOGITS
    for
    0.86
    V
    0.79
    ו
    0.78
    It
    0.74
    Our
    0.74
    For
    0.73
    N
    0.73
    Remote
    0.72
    you
    0.72
    UR
    0.71
    Activations Density 0.002%

    No Known Activations