© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 101671
    Prev
    Next
    INDEX
    Explanations

    subtract

    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_44_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
     computation
    0.48
     calculation
    0.44
    <0x96>
    0.40
    算的
    0.40
     computational
    0.40
     计算
    0.39
     computations
    0.39
     calculations
    0.39
    +,
    0.39
    十三
    0.39
    POSITIVE LOGITS
     полю
    0.39
     fk
    0.36
    ണു
    0.35
     스토리
    0.34
    軹
    0.34
    มากขึ้น
    0.33
    म्मद
    0.33
    นคร
    0.32
    ။
    0.32
    gambar
    0.32
    Activations Density 0.002%

    No Known Activations