© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 236421
    Prev
    Next
    INDEX
    Explanations

    multiplication and calculation results

    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_32_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
     बगैर
    0.39
     बिना
    0.39
    이에요
    0.36
     বিনা
    0.35
     <?
    0.34
     Processes
    0.34
     reflexive
    0.34
     escoger
    0.34
     বাংলাদেশকে
    0.34
     அனை
    0.34
    POSITIVE LOGITS
    ⁧
    0.38
    これらの
    0.35
     Vikt
    0.35
    வ்வாறு
    0.34
     COULD
    0.34
    Walt
    0.34
    Witt
    0.34
     encar
    0.34
    Vehicle
    0.33
     THESE
    0.33
    Activations Density 0.004%

    No Known Activations