© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 64113
    Prev
    Next
    INDEX
    Explanations

    Ko

    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_59_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
    િયાન
    0.46
    IANA
    0.46
     Martyn
    0.43
    ೆಂ
    0.42
    iensis
    0.42
    RegistrationBean
    0.41
     Martina
    0.39
    桓
    0.38
    ianas
    0.38
    iana
    0.38
    POSITIVE LOGITS
    ls
    0.52
    long
    0.52
    lg
    0.52
    los
    0.52
    pu
    0.50
    pur
    0.50
    lah
    0.50
    lf
    0.50
    nde
    0.50
    lü
    0.49
    Activations Density 0.001%

    No Known Activations