© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169574
    Prev
    Next
    INDEX
    Explanations

    letter j

    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_56_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
    avras
    0.39
    ண்ணாம
    0.36
     पटाखे
    0.34
    erts
    0.34
    handlungen
    0.33
    amburger
    0.33
    摑
    0.33
    ابی
    0.32
    itva
    0.31
    ágot
    0.31
    POSITIVE LOGITS
     j
    3.14
     ج
    2.06
     ज
    1.72
    j
    1.67
     জ
    1.59
    จ
    1.53
     ж
    1.51
     m
    1.30
     J
    1.25
    ｊ
    1.25
    Activations Density 0.014%

    No Known Activations