© 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
    2. Gemma-3-27B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 125793
    Prev
    Next
    INDEX
    Explanations

    rich and poor, or people's names

    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_3_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
    ),”
    0.69
    is
    0.65
    ेंस
    0.64
    น
    0.59
    ),"
    0.58
    ).”
    0.58
    ަނ
    0.58
    е
    0.58
    ะ
    0.57
    .”)
    0.56
    POSITIVE LOGITS
    3
    0.63
    Sec
    0.57
    Produkt
    0.52
    Mining
    0.52
    。
    0.52
    Product
    0.51
    7
    0.50
     غير
    0.50
    Kitchen
    0.50
    Pizza
    0.50
    Activations Density 0.000%

    No Known Activations