© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 32-GEMMASCOPE-2-TRANSCODER-262K
    4. 233689
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connectors

    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_32_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
    Branch
    0.42
    hran
    0.41
    WebV
    0.40
    ×</
    0.39
    })$;
    0.39
     तीनों
    0.38
     आँख
    0.38
    OGR
    0.38
     furl
    0.38
    branch
    0.38
    POSITIVE LOGITS
     And
    0.54
     และ
    0.52
     અને
    0.51
     এবং
    0.51
     iar
    0.48
     आणि
    0.47
    而
    0.45
     и
    0.44
     وهذا
    0.43
     और
    0.43
    Activations Density 0.028%

    No Known Activations