© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 35543
    Prev
    Next
    INDEX
    Explanations

    information retrieval

    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_3_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
    k
    0.78
    ir
    0.77
    ia
    0.67
    ic
    0.65
    utt
    0.64
    do
    0.63
    ник
    0.63
    rt
    0.62
    ن
    0.62
    ike
    0.61
    POSITIVE LOGITS
     is
    0.87
    L
    0.86
    B
    0.83
     sadr
    0.73
    Ста
    0.72
     godina
    0.70
    ياب
    0.69
    は
    0.68
    اني
    0.68
    ﹒
    0.68
    Activations Density 0.007%

    No Known Activations