© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 195678
    Prev
    Next
    INDEX
    Explanations

    **RBC**

    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_4_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
    ะ
    0.13
     preocup
    0.12
    ando
    0.11
     participaron
    0.11
    人不
    0.11
     continuare
    0.11
    দিন
    0.11
     prosegu
    0.11
    یان
    0.11
    ין
    0.11
    POSITIVE LOGITS
    v
    0.14
    st
    0.13
    та
    0.12
    ט
    0.12
     در
    0.10
    ۔
    0.10
    et
    0.10
    tissue
    0.10
    ática
    0.10
    sette
    0.10
    Activations Density 0.001%

    No Known Activations