© 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
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 61784
    Prev
    Next
    INDEX
    Explanations

    plotting

    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_59_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
    ા
    0.41
     supermarket
    0.37
    ole
    0.37
    ोले
    0.37
    正常的
    0.36
    蛲
    0.35
     discussions
    0.34
    suggestion
    0.34
     bowel
    0.34
    ب
    0.34
    POSITIVE LOGITS
    }^{\
    0.43
     أيضاً
    0.42
    vtk
    0.42
    Staying
    0.41
    itud
    0.41
    Ins
    0.41
    Checkbox
    0.41
    Ethyl
    0.40
    UpDown
    0.40
    urtle
    0.40
    Activations Density 0.002%

    No Known Activations