© 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. 47232
    Prev
    Next
    INDEX
    Explanations

    decibel-milliwatts

    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
    t
    1.20
    al
    0.92
    is
    0.88
    l
    0.84
    s
    0.81
     discontinue
    0.79
    p
    0.77
    it
    0.74
    of
    0.74
    d
    0.74
    POSITIVE LOGITS
    高达
    0.71
     ০
    0.68
    她的
    0.67
    一些
    0.66
    高志森
    0.65
     ৭
    0.64
    屽
    0.64
    垡
    0.63
    لي
    0.63
    نو
    0.61
    Activations Density 0.001%

    No Known Activations