© 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-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 6705
    Prev
    Next
    INDEX
    Explanations

    Gruyere cheese

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_3_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
    𝐃
    0.72
     analyte
    0.59
     onOptions
    0.59
    लिब्र
    0.58
    nger
    0.58
    রী
    0.57
     intravenously
    0.56
    夫
    0.56
    çok
    0.56
     식으로
    0.56
    POSITIVE LOGITS
     przest
    0.58
    <th>
    0.57
    ()=>{
    0.57
    きっと
    0.57
     انقلاب
    0.55
    s
    0.54
     zanim
    0.53
     montar
    0.53
    на
    0.52
    ాన్
    0.51
    Activations Density 0.001%

    No Known Activations