© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 93265
    Prev
    Next
    INDEX
    Explanations

    accounting and financial statements

    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_11_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
    </strong>
    0.65
     complesso
    0.59
    を果た
    0.57
    ्डा
    0.57
    вершена
    0.56
     limitado
    0.55
    і
    0.55
    दर्शिता
    0.54
    یسم
    0.54
     edifício
    0.54
    POSITIVE LOGITS
    r
    0.55
     intuit
    0.53
     AT
    0.53
     aswell
    0.52
     in
    0.51
     ProductCategory
    0.50
     around
    0.50
    t
    0.49
     as
    0.49
    ).
    0.49
    Activations Density 0.007%

    No Known Activations