© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48807
    Prev
    Next
    INDEX
    Explanations

    say the

    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_55_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
     профе
    0.41
     uncomment
    0.38
     números
    0.35
    ﺝ
    0.34
     profes
    0.33
     klasik
    0.32
     unsettling
    0.31
     entweder
    0.31
     obvi
    0.31
     vuccanti
    0.31
    POSITIVE LOGITS
     th
    0.55
     ther
    0.41
     socialism
    0.40
     ofthe
    0.39
     teh
    0.38
    ann
    0.38
     thi
    0.38
     Socialism
    0.38
    ʲ
    0.37
    ukannya
    0.37
    Activations Density 0.010%

    No Known Activations