© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 130
    Prev
    Next
    INDEX
    Explanations

    US states

    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_40_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
     Rutland
    0.41
    Sim
    0.38
    ()");
    0.38
     tvor
    0.38
    lun
    0.37
    ？](
    0.37
    Vermont
    0.37
    สห
    0.37
    cott
    0.36
    陼
    0.36
    POSITIVE LOGITS
    షి
    0.44
    гээ
    0.40
     comod
    0.40
    üssel
    0.38
     श्रृंखला
    0.38
     NM
    0.37
     mocker
    0.37
     Chama
    0.37
     Turbo
    0.37
    Turbo
    0.37
    Activations Density 0.018%

    No Known Activations