© 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. 30869
    Prev
    Next
    INDEX
    Explanations

    currency and quantity

    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
    "=
    0.41
    rossover
    0.37
     reverses
    0.37
    velle
    0.37
    écies
    0.36
    ulter
    0.36
     creeks
    0.36
    创
    0.35
     قيمه
    0.35
     processor
    0.34
    POSITIVE LOGITS
     tens
    0.66
    Tens
    0.63
     десятки
    0.62
    几
    0.59
    tens
    0.56
    几十
    0.56
     hundreds
    0.55
     dozens
    0.55
    幾
    0.55
     Hundreds
    0.55
    Activations Density 0.012%

    No Known Activations