© 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. 196059
    Prev
    Next
    INDEX
    Explanations

    Computer-Aided Design or Drug

    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
     to
    0.12
     on
    0.12
     up
    0.11
     b
    0.11
     k
    0.11
    টি
    0.10
     är
    0.10
     j
    0.10
     ö
    0.10
     x
    0.10
    POSITIVE LOGITS
    r
    0.13
    l
    0.13
    t
    0.13
    و
    0.13
    da
    0.12
     Ирина
    0.12
    p
    0.12
    na
    0.12
    các
    0.11
     ettha
    0.11
    Activations Density 0.003%

    No Known Activations