© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81717
    Prev
    Next
    INDEX
    Explanations

    Kubernetes

    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_0_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
    า
    2.14
     I
    2.13
    </h3>
    1.65
     を
    1.41
    ק
    1.40
     と
    1.37
    </h4>
    1.34
    サ
    1.32
    ડ
    1.30
    تی
    1.27
    POSITIVE LOGITS
    ت
    2.05
    ни
    1.85
    ون
    1.38
    一
    1.30
    é
    1.29
    aneous
    1.25
    j
    1.24
    ine
    1.23
    ’
    1.23
    né
    1.22
    Activations Density 0.004%

    No Known Activations