© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 229678
    Prev
    Next
    INDEX
    Explanations

    hyperventilation, hypervigilance, hyperexcitability

    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_6_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
    ↵
    1.19
    ;
    0.99
    4
    0.98
     hvilket
    0.97
    =
    0.95
     ਜਾਂ
    0.93
    9
    0.93
    .
    0.92
    ).
    0.88
    0
    0.88
    POSITIVE LOGITS
     It
    1.13
    on
    1.09
    ir
    1.09
    un
    1.02
    to
    1.02
    зывает
    0.99
     presentes
    0.97
    ী
    0.96
    ínt
    0.95
    onar
    0.93
    Activations Density 0.001%

    No Known Activations