© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 49188
    Prev
    Next
    INDEX
    Explanations

    Biblical books

    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
    👎
    0.42
     desplazamiento
    0.38
    Hig
    0.37
    📥
    0.37
     отвер
    0.36
     удовлетво
    0.35
    ње
    0.35
     Цер
    0.35
    substituted
    0.35
     համար
    0.35
    POSITIVE LOGITS
    lap
    0.37
    Hire
    0.37
    井
    0.37
     வைர
    0.37
    agata
    0.37
    oland
    0.36
    照
    0.36
    wells
    0.36
    গন্ধ
    0.36
     subspecies
    0.36
    Activations Density 0.001%

    No Known Activations