© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 150421
    Prev
    Next
    INDEX
    Explanations

    commodification, agribusiness, scams, Genius

    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_23_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
    裴
    0.32
    functional
    0.31
    Yes
    0.30
    Functional
    0.29
    synt
    0.29
    attention
    0.29
    PRES
    0.28
     samostat
    0.28
    甭
    0.28
    RelativeLayout
    0.28
    POSITIVE LOGITS
     caché
    0.32
     Clique
    0.31
     Salmonella
    0.31
     unut
    0.31
     Cache
    0.30
     paranoid
    0.30
     autoWatch
    0.30
     enabled
    0.29
     unsol
    0.29
     skaters
    0.29
    Activations Density 0.015%

    No Known Activations