© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 152018
    Prev
    Next
    INDEX
    Explanations

    vtuber

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    imes
    0.69
    arget
    0.68
    ree
    0.68
    ः
    0.68
    odo
    0.65
    ouch
    0.64
    ype
    0.64
    ools
    0.64
    ime
    0.63
    itle
    0.63
    POSITIVE LOGITS
    ار
    0.51
    ט
    0.50
    ות
    0.44
    ்ச
    0.44
    ات
    0.43
    ة
    0.43
    ad
    0.42
    ்ப
    0.42
    ล
    0.42
    atein
    0.41
    Activations Density 0.002%

    No Known Activations