© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 153003
    Prev
    Next
    INDEX
    Explanations

    calculating differences and percentages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_23_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
    mpl
    0.44
    மய
    0.43
    پل
    0.41
    bür
    0.41
    {{\
    0.40
     redd
    0.40
    hör
    0.39
    icult
    0.38
    hört
    0.38
    ایه
    0.38
    POSITIVE LOGITS
    減少
    0.40
    ಲ್ಲೂ
    0.39
     Respir
    0.39
     également
    0.38
     শুভেচ্ছা
    0.38
     mengen
    0.37
     Steady
    0.37
     तल
    0.37
    車
    0.37
     等
    0.36
    Activations Density 0.003%

    No Known Activations