© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 3596
    Prev
    Next
    INDEX
    Explanations

    Moscow, Economic Development, Memory

    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_40_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
    queued
    0.38
    Ｘ
    0.38
    準備
    0.37
     Spit
    0.35
     бил
    0.35
    ക്കം
    0.35
    தய
    0.35
    ]<<
    0.33
     dirigir
    0.33
    transmit
    0.33
    POSITIVE LOGITS
    ongi
    0.42
    ahl
    0.39
    犍
    0.36
     ನ
    0.36
    áns
    0.35
     scho
    0.35
    inthe
    0.35
     September
    0.35
    aza
    0.35
    esco
    0.34
    Activations Density 0.010%

    No Known Activations