© 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. 246488
    Prev
    Next
    INDEX
    Explanations

    multiplication of large numbers

    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
     unità
    0.39
    yska
    0.39
    perg
    0.37
    thisobject
    0.37
    alada
    0.36
    䒴
    0.36
    openzeppelin
    0.36
    馍
    0.35
    doğan
    0.34
     impediments
    0.34
    POSITIVE LOGITS
     hundred
    0.54
    Hundreds
    0.44
     Hundreds
    0.44
     cientos
    0.43
    hundred
    0.43
    二百
    0.43
     hundreds
    0.42
    百
    0.42
    一百
    0.41
     notifying
    0.41
    Activations Density 0.007%

    No Known Activations