© 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. 101560
    Prev
    Next
    INDEX
    Explanations

    a

    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
     timescales
    0.44
     zabezpie
    0.40
     살아
    0.40
     predictions
    0.40
     Supplemental
    0.39
    виль
    0.39
     زندہ
    0.39
     données
    0.39
     tarde
    0.38
    筏
    0.38
    POSITIVE LOGITS
     sai
    0.37
    τας
    0.36
     cet
    0.36
    elj
    0.35
    Pause
    0.35
    ropole
    0.35
     rud
    0.35
    erkt
    0.34
     Jü
    0.34
     voice
    0.34
    Activations Density 0.004%

    No Known Activations