© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196245
    Prev
    Next
    INDEX
    Explanations

    Hubert

    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_46_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nden
    0.41
    ты
    0.39
     whakar
    0.39
    囘
    0.39
    ologías
    0.38
    欠
    0.36
    lateral
    0.36
     তাই
    0.36
    blasts
    0.36
     недоста
    0.35
    POSITIVE LOGITS
     movers
    0.41
    電
    0.38
     reprints
    0.38
     stamped
    0.38
     spit
    0.38
     stigma
    0.37
     acuerdo
    0.36
     HttpResponse
    0.35
    neau
    0.35
     evenly
    0.35
    Activations Density 0.000%

    No Known Activations