© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 199070
    Prev
    Next
    INDEX
    Explanations

    map values, columns, conditions

    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_12_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
    ни
    0.72
    ر
    0.64
     andere
    0.64
    ι
    0.62
    يل
    0.61
    ut
    0.59
    獭
    0.57
    у
    0.55
    и
    0.55
     其他
    0.54
    POSITIVE LOGITS
    Cause
    0.62
     alignment
    0.61
    Las
    0.59
    BI
    0.57
    ALIGN
    0.55
    Born
    0.54
    Baş
    0.53
    Clothes
    0.53
    Newton
    0.52
    ShoppingCart
    0.52
    Activations Density 0.008%

    No Known Activations