© 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. 510
    Prev
    Next
    INDEX
    Explanations

    python imports

    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
    Metallic
    0.41
     posl
    0.41
    ോഷ
    0.39
     पॅ
    0.39
    هو
    0.38
     Metallic
    0.37
    ಸ್ತು
    0.37
    黉
    0.36
     luc
    0.36
     کرو
    0.36
    POSITIVE LOGITS
     Star
    0.41
     STAR
    0.39
    async
    0.38
    anie
    0.38
     springtime
    0.38
    ASGI
    0.38
    hyper
    0.38
    uv
    0.37
    iquet
    0.37
    hpp
    0.37
    Activations Density 0.240%

    No Known Activations