© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 208466
    Prev
    Next
    INDEX
    Explanations

    attributing quotes after "said"

    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
     vuole
    0.80
     το
    0.71
     appelez
    0.69
     に
    0.64
     取っ
    0.64
    鈈
    0.64
     chodzi
    0.63
     indiquer
    0.63
    ους
    0.63
    込んだ
    0.62
    POSITIVE LOGITS
     be
    0.91
    ت
    0.77
    t
    0.76
    be
    0.73
    tv
    0.71
    м
    0.68
    م
    0.67
    0.66
     on
    0.66
    मक
    0.65
    Activations Density 0.000%

    No Known Activations