© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 30920
    Prev
    Next
    INDEX
    Explanations

    intrinsic

    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_50_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
    sna
    0.41
     je
    0.41
    Je
    0.38
    เจ
    0.38
    គ្ន
    0.37
    ruf
    0.37
     রূপ
    0.36
     Nt
    0.36
    teg
    0.36
    菽
    0.36
    POSITIVE LOGITS
    ins
    0.54
    insa
    0.53
    insi
    0.45
    rins
    0.43
     ari
    0.40
     Ari
    0.40
    nsic
    0.40
     Ins
    0.39
     reinforcement
    0.38
    ᾿
    0.37
    Activations Density 0.007%

    No Known Activations