© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39833
    Prev
    Next
    INDEX
    Explanations

    คำอธิบาย, คำถาม

    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
    Negative Logits
    </h2>
    0.82
    ন
    0.82
    ла
    0.81
    та
    0.79
    </b>
    0.76
    ור
    0.73
    ро
    0.73
    ва
    0.73
    ู
    0.72
    р
    0.72
    POSITIVE LOGITS
    c
    0.88
    g
    0.87
    b
    0.83
    cích
    0.75
    d
    0.75
    bies
    0.74
    érer
    0.68
    ires
    0.66
    keit
    0.66
    vány
    0.66
    Activations Density 0.000%

    No Known Activations