© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 197775
    Prev
    Next
    INDEX
    Explanations

    forest service

    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_4_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
    is
    1.07
     וא
    0.97
     reconoc
    0.91
     ও
    0.89
     и
    0.88
    s
    0.88
     sév
    0.85
     व
    0.84
     và
    0.83
     reflet
    0.83
    POSITIVE LOGITS
    ।
    0.92
    로
    0.89
    。
    0.87
    1
    0.87
    '
    0.87
    ка
    0.86
    р
    0.83
    시
    0.82
    IfExists
    0.81
    پ
    0.81
    Activations Density 0.001%

    No Known Activations