© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195594
    Prev
    Next
    INDEX
    Explanations

    do not force

    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_27_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
    Adjust
    0.45
    ্লেখ
    0.40
    adjust
    0.38
    Fig
    0.38
     Adjust
    0.37
     adjustments
    0.35
    জেন
    0.35
    ]}{
    0.34
     മുത
    0.34
     jana
    0.34
    POSITIVE LOGITS
     निदेश
    0.38
     Walnut
    0.37
    getImageFolder
    0.36
     isAdmin
    0.35
     книг
    0.35
    मपुर
    0.35
    rières
    0.35
    십
    0.35
     contest
    0.35
     города
    0.35
    Activations Density 0.005%

    No Known Activations