© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 228870
    Prev
    Next
    INDEX
    Explanations

    Indonesian/Malay "aku"

    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_6_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
     Vereinigten
    0.88
    ،
    0.82
    ze
    0.82
     നിന്ന്
    0.82
    ция
    0.81
    يل
    0.80
    씩
    0.80
    ات
    0.79
    的需求
    0.79
    nych
    0.79
    POSITIVE LOGITS
     in
    1.70
    在
    1.27
    ;
    1.13
    0
    1.10
     inorder
    1.05
    ي
    0.98
    f
    0.98
    g
    0.97
    A
    0.96
    ０
    0.93
    Activations Density 0.000%

    No Known Activations