© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 200457
    Prev
    Next
    INDEX
    Explanations

    after the

    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_6_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
    ض
    1.14
    ین
    1.10
    ظ
    1.09
    ط
    1.06
    ات
    1.05
    ي
    1.04
    द
    1.02
    서는
    1.00
    적
    0.98
    단
    0.98
    POSITIVE LOGITS
    on
    0.93
     he
    0.92
    0.91
     are
    0.88
    iles
    0.85
     for
    0.84
    ena
    0.83
     FIXME
    0.82
    iri
    0.82
    ly
    0.81
    Activations Density 0.001%

    No Known Activations