© 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. 39925
    Prev
    Next
    INDEX
    Explanations

    accomplish, achieve, or rise

    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
    m
    1.13
    ti
    1.03
    s
    0.96
    tr
    0.91
    g
    0.91
    v
    0.90
    j
    0.88
    si
    0.88
    ta
    0.87
    k
    0.86
    POSITIVE LOGITS
    amiento
    0.71
    ानुसार
    0.66
    AT
    0.64
    Фу
    0.64
    ados
    0.62
    DRA
    0.62
    amble
    0.61
    amaged
    0.60
    amaks
    0.60
    ificacion
    0.59
    Activations Density 0.209%

    No Known Activations