© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117011
    Prev
    Next
    INDEX
    Explanations

    forms of government

    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
     Geos
    0.33
     Auxiliary
    0.31
     CT
    0.31
     dataset
    0.30
    Aux
    0.30
     sedimentation
    0.30
    貶
    0.30
     Version
    0.29
     augment
    0.29
    ევ
    0.29
    POSITIVE LOGITS
     फोन
    0.37
     thereunder
    0.37
     रूल
    0.35
    លោក
    0.35
     पाकिस्तानी
    0.35
     ống
    0.34
    athar
    0.34
    }-
    0.34
     tự
    0.33
    পুরের
    0.33
    Activations Density 0.007%

    No Known Activations