© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 29782
    Prev
    Next
    INDEX
    Explanations

    idioms and expressions

    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_40_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
     toug
    0.41
    дук
    0.37
    }(-\
    0.36
     (-)
    0.36
    }}}{\
    0.35
     systém
    0.35
    mut
    0.34
     систему
    0.34
    do
    0.33
     Mot
    0.33
    POSITIVE LOGITS
    क्रीम
    0.48
    🐴
    0.41
    Rejected
    0.40
    York
    0.39
     kopi
    0.38
     forhold
    0.38
    ᠨ
    0.38
    ピュー
    0.38
     ubicación
    0.37
     fileCopy
    0.37
    Activations Density 0.000%

    No Known Activations