© 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
    2. Gemma-3-27B-IT
    3. 20-GEMMASCOPE-2-TRANSCODER-262K
    4. 173788
    Prev
    Next
    INDEX
    Explanations

    API keys and secrets

    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
    ytu
    0.43
     harta
    0.43
    牺
    0.41
     regarder
    0.40
    েলে
    0.40
     बलिदान
    0.39
     dielectric
    0.38
    oszt
    0.38
    êmes
    0.38
    veld
    0.38
    POSITIVE LOGITS
    _
    0.43
     для
    0.38
     Things
    0.38
     Waterfront
    0.38
    #[
    0.37
    Chúng
    0.37
     "
    0.36
     від
    0.36
    Developing
    0.36
     talento
    0.36
    Activations Density 0.001%

    No Known Activations