© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 197300
    Prev
    Next
    INDEX
    Explanations

    identify people/things

    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
     aged
    1.30
     ≥
    1.04
     >=
    1.00
     $>
    1.00
     ≤
    0.99
     Aged
    0.98
     berusia
    0.98
     $<
    0.98
     between
    0.96
     âg
    0.91
    POSITIVE LOGITS
     outermost
    0.37
    ぅ
    0.34
     secondaire
    0.34
    meson
    0.34
    nitz
    0.33
    Bm
    0.33
    rowse
    0.33
    ද්ග
    0.33
     ደ
    0.32
    র্ড
    0.32
    Activations Density 0.040%

    No Known Activations