© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 64451
    Prev
    Next
    INDEX
    Explanations

    the number 5

    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_46_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
     നാല
    0.62
     four
    0.61
     Four
    0.61
     fourth
    0.59
    四
    0.59
     bốn
    0.59
     dört
    0.59
     четвер
    0.56
     czter
    0.56
     चार
    0.55
    POSITIVE LOGITS
    اسی
    0.46
    <0xB2>
    0.45
    6
    0.45
    ٦
    0.43
    ๖
    0.43
    ೭
    0.43
     sixty
    0.41
     Sixth
    0.41
    Three
    0.40
     ۱۳
    0.39
    Activations Density 0.009%

    No Known Activations