© 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. 35740
    Prev
    Next
    INDEX
    Explanations

    ancient structures and ruins

    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
     abst
    0.39
    pooling
    0.39
     અમે
    0.38
    genesis
    0.37
    niew
    0.36
     پاکستان
    0.36
    poder
    0.36
    诮
    0.36
    ườn
    0.35
     Ishikawa
    0.35
    POSITIVE LOGITS
     lob
    0.39
     ڈاک
    0.39
    acart
    0.38
    谟
    0.36
     enak
    0.36
    abola
    0.36
     चक्रवृद्धि
    0.35
    scdn
    0.35
     ém
    0.35
     דער
    0.35
    Activations Density 0.019%

    No Known Activations