© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36516
    Prev
    Next
    INDEX
    Explanations

    office, relations, consequences

    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_11_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
     Kähler
    0.61
     whitish
    0.59
     pár
    0.57
     lepší
    0.55
    ﮯ
    0.54
     до
    0.54
     mét
    0.52
    ído
    0.52
     Marxist
    0.51
     mỹ
    0.51
    POSITIVE LOGITS
    _),
    0.64
    es
    0.63
    na
    0.61
    Также
    0.61
    osil
    0.60
    ni
    0.60
    li
    0.59
    அ
    0.59
    ak
    0.59
    ate
    0.58
    Activations Density 0.003%

    No Known Activations