© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173476
    Prev
    Next
    INDEX
    Explanations

    offers and serves

    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_20_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
     criança
    0.36
     সাহায
    0.33
    ură
    0.33
    нче
    0.32
     dziecko
    0.32
     ध
    0.32
    加工
    0.31
     बचत
    0.31
    Modify
    0.31
    糹
    0.30
    POSITIVE LOGITS
    들에
    0.29
     loudest
    0.29
    鸷
    0.29
    ைகளை
    0.29
     speeches
    0.29
     ఏమి
    0.28
     theses
    0.27
     moths
    0.27
    <0xBE>
    0.27
     nerves
    0.26
    Activations Density 0.004%

    No Known Activations