© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 45159
    Prev
    Next
    INDEX
    Explanations

    modern monetary theory

    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_22_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
    േഷ്
    0.48
     minimal
    0.47
    셸
    0.45
     bones
    0.44
     mamm
    0.43
     alkalmaz
    0.43
     deformations
    0.42
     commens
    0.42
     pronotum
    0.40
     seashells
    0.40
    POSITIVE LOGITS
     Dieser
    0.41
     Trag
    0.40
    ឆ
    0.38
    消失
    0.38
     ধ্বংস
    0.38
    ຈາກ
    0.38
    ifiably
    0.38
     वृद्ध
    0.37
    CF
    0.37
     Suche
    0.37
    Activations Density 0.000%

    No Known Activations