© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31746
    Prev
    Next
    INDEX
    Explanations

    list item keywords

    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_31_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
     compartmental
    0.39
     Version
    0.37
     গাড়ীতে
    0.36
    왑
    0.36
    дился
    0.36
    ారు
    0.36
     compartment
    0.35
    న్నారు
    0.34
     formalism
    0.34
    дра
    0.34
    POSITIVE LOGITS
     alebo
    0.45
     或
    0.45
    racción
    0.44
    或者
    0.42
    nač
    0.41
    orthy
    0.40
    omen
    0.39
     veya
    0.38
    ,"%
    0.38
     तेरी
    0.37
    Activations Density 0.004%

    No Known Activations