© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 1420
    Prev
    Next
    INDEX
    Explanations

    government schemes and public services

    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_39_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
     Campus
    0.37
     Practices
    0.37
    bor
    0.36
    举
    0.35
    ibor
    0.34
    вт
    0.34
    θεν
    0.33
    jakarta
    0.33
     bake
    0.33
    acky
    0.33
    POSITIVE LOGITS
    หมู่
    0.43
     electrified
    0.41
    connectivity
    0.41
    佻
    0.38
     speedy
    0.38
     yoj
    0.38
     schemes
    0.38
    Availability
    0.37
     शौचाल
    0.37
     digitalization
    0.37
    Activations Density 0.012%

    No Known Activations