© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159564
    Prev
    Next
    INDEX
    Explanations

    MBTA

    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_2_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
    is
    1.45
    ↵↵
    1.39
    у
    1.27
    -
    1.24
    am
    1.19
    ’
    1.13
    +
    1.09
    ר
    1.06
    th
    1.04
    ༢
    1.03
    POSITIVE LOGITS
    h
    1.21
    ل
    1.21
     as
    1.12
    ก
    1.11
    ant
    1.06
    い
    1.03
    نا
    1.00
    rets
    0.99
    auks
    0.96
     genitalia
    0.96
    Activations Density 0.001%

    No Known Activations