© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12853
    Prev
    Next
    INDEX
    Explanations

    Firefox

    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
    าด
    0.41
     AIP
    0.37
    ुर्
    0.36
     काढ
    0.35
     โร
    0.34
     Pavia
    0.34
    ্দ
    0.34
    痪
    0.34
     Milan
    0.34
     trainer
    0.34
    POSITIVE LOGITS
    kode
    0.43
     Leica
    0.39
    cross
    0.38
    દેશ
    0.38
    œ
    0.38
    codes
    0.37
    ivore
    0.37
    Kod
    0.37
    धिकारियों
    0.36
    content
    0.36
    Activations Density 0.001%

    No Known Activations