© 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. 16-GEMMASCOPE-2-TRANSCODER-262K
    7. 100390
    Prev
    Next
    INDEX
    Explanations

    st.table

    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_16_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
    mores
    0.22
    ar
    0.20
    better
    0.20
    Better
    0.20
    bic
    0.20
    social
    0.20
    Για
    0.20
    b
    0.20
    Net
    0.20
    source
    0.19
    POSITIVE LOGITS
    ต
    0.24
    лизм
    0.22
     marshes
    0.22
     бор
    0.22
     escolh
    0.22
     marais
    0.21
     pessoais
    0.21
     personen
    0.21
    ')$
    0.21
     mantras
    0.21
    Activations Density 0.017%

    No Known Activations