© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 30724
    Prev
    Next
    INDEX
    Explanations

    Department of

    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_7_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
     피부
    0.29
     ਦੀ
    0.29
     或
    0.28
     లేదా
    0.28
    ☏
    0.27
     அல்லது
    0.27
    _"+
    0.27
    ਾਰ
    0.27
    ApiException
    0.27
    tFileInputExcel
    0.26
    POSITIVE LOGITS
     The
    0.44
    ه
    0.42
     THE
    0.40
    ה
    0.39
    The
    0.38
    w
    0.35
    те
    0.35
    ك
    0.34
    ع
    0.33
    ط
    0.32
    Activations Density 0.001%

    No Known Activations