© 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
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31191
    Prev
    Next
    INDEX
    Explanations

    n

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    vart
    0.42
    dash
    0.40
    co
    0.39
    ραγ
    0.39
    artis
    0.39
    basin
    0.38
    螟
    0.37
    Dash
    0.37
    cess
    0.37
     গার্ডিয়ান
    0.37
    POSITIVE LOGITS
    ema
    0.52
    EMA
    0.51
    ama
    0.49
     AMA
    0.49
     EMA
    0.47
     Ama
    0.46
     ema
    0.43
     IMA
    0.40
    eri
    0.40
    🍑
    0.40
    Activations Density 0.006%

    No Known Activations