© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208427
    Prev
    Next
    INDEX
    Explanations

    sales made or generated

    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_20_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
     monatomic
    0.50
     AcOH
    0.47
    вих
    0.45
     COMPOUNDS
    0.45
     OSM
    0.44
     biofuels
    0.43
    𝙳
    0.43
     sulfide
    0.43
     नाइट्रोजन
    0.43
     defamation
    0.43
    POSITIVE LOGITS
    grö
    0.47
    =
    0.44
     &
    0.43
    field
    0.42
    edy
    0.40
    *)
    0.39
    idis
    0.39
    langs
    0.39
    iden
    0.38
    ovis
    0.38
    Activations Density 0.001%

    No Known Activations