© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50180
    Prev
    Next
    INDEX
    Explanations

    saw the

    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_31_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
    pdfs
    0.40
     регули
    0.40
    jegyz
    0.37
     ഇപ്പോ
    0.36
    依然
    0.36
     socialize
    0.36
    漑
    0.36
     рэгістра
    0.35
     dissipative
    0.35
     adequately
    0.35
    POSITIVE LOGITS
     درمان
    0.38
    ymas
    0.38
    ທີ່ມີ
    0.37
     appealing
    0.36
     délégation
    0.36
    ど
    0.36
    uniqueItems
    0.35
    rius
    0.35
    start
    0.35
     extremal
    0.34
    Activations Density 0.002%

    No Known Activations