© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 61549
    Prev
    Next
    INDEX
    Explanations

    disorder or process ending

    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_2_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
    ت
    1.75
    um
    1.69
    0
    1.55
    ات
    1.37
     for
    1.35
    uts
    1.27
    ا
    1.27
    os
    1.27
    ant
    1.23
    en
    1.23
    POSITIVE LOGITS
    )%>%
    0.93
     catchment
    0.93
    キャンペーン
    0.93
    "%
    0.91
     şekilde
    0.91
    AVE
    0.90
    л
    0.90
    ב
    0.87
    سی
    0.86
    January
    0.86
    Activations Density 0.005%

    No Known Activations