© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 50673
    Prev
    Next
    INDEX
    Explanations

    logical operators and list/array operations

    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_30_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
     “‘
    0.32
     enfim
    0.32
     τὴν
    0.32
    -%
    0.31
     ″
    0.31
    ۷
    0.31
    ಡಿಯ
    0.30
    وان
    0.30
     valamint
    0.30
    grunge
    0.30
    POSITIVE LOGITS
     squre
    0.51
    룔
    0.46
    劵
    0.46
    weig
    0.42
     phosphorous
    0.42
     lenght
    0.42
    postion
    0.42
    ㅍ
    0.41
    frist
    0.40
    朿
    0.40
    Activations Density 0.025%

    No Known Activations