© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 120478
    Prev
    Next
    INDEX
    Explanations

    question words asking "how many" or "where is"

    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_27_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
     ஆணைய
    0.38
    лені
    0.38
     Без
    0.38
    次に
    0.37
    এমন
    0.36
     grab
    0.36
    后面
    0.36
    <0xD1>
    0.35
    NB
    0.35
     Fußball
    0.35
    POSITIVE LOGITS
     ప్రకృతి
    0.39
     naturais
    0.38
    சாலை
    0.38
    uirre
    0.38
     ureth
    0.37
     ub
    0.36
     reminiscent
    0.36
     naturalist
    0.36
    ùi
    0.36
    semantics
    0.36
    Activations Density 0.005%

    No Known Activations