© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170933
    Prev
    Next
    INDEX
    Explanations

    afford to lose money

    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_20_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
    ويه
    0.41
     Jeans
    0.40
    <0x8F>
    0.39
     relaxes
    0.38
     நிர
    0.38
    words
    0.37
     emerges
    0.35
    В
    0.35
     Supporting
    0.34
    Supporting
    0.34
    POSITIVE LOGITS
    णाल
    0.46
    龔
    0.44
     pulmonary
    0.43
    ايبي
    0.43
     pollute
    0.43
     penthouse
    0.42
    ராட்சி
    0.42
    政府采购
    0.42
    yank
    0.41
     distillate
    0.41
    Activations Density 0.005%

    No Known Activations