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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164828
    Prev
    Next
    INDEX
    Explanations

    numbers followed by `+` or `-` operators

    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_13_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
    de
    0.42
    '])]
    0.40
    DE
    0.39
    YEAR
    0.37
    Fecha
    0.36
    ibling
    0.35
    <0xA4>
    0.35
    DATE
    0.35
     DE
    0.34
    Hay
    0.34
    POSITIVE LOGITS
    ｗｗ
    0.38
    webstore
    0.38
    za
    0.36
    μι
    0.36
    zonego
    0.36
     ব্রিটেন
    0.35
    "
    0.35
     Брита
    0.34
    ेक्ट
    0.34
    that
    0.33
    Activations Density 0.005%

    No Known Activations