© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 210111
    Prev
    Next
    INDEX
    Explanations

    handling alternatives or contrasts

    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_19_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
    /
    0.23
    Chinese
    0.22
     نے
    0.22
     unde
    0.21
     z
    0.21
    ври
    0.21
     such
    0.21
     Unde
    0.21
     nauk
    0.21
    ரி
    0.21
    POSITIVE LOGITS
    нг
    0.25
     पंत
    0.25
    َق
    0.24
    ♤
    0.24
    ichever
    0.23
    َم
    0.23
    hilfe
    0.23
    ัล
    0.23
    ಚ್
    0.23
    кал
    0.23
    Activations Density 0.044%

    No Known Activations