© 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. 6841
    Prev
    Next
    INDEX
    Explanations

    scenic route or views

    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
    是
    0.65
    斯的
    0.62
     оказалось
    0.62
    로
    0.59
    𝖙
    0.58
    是因为
    0.57
    𝖑
    0.55
    кла
    0.55
     получилось
    0.55
     dinner
    0.55
    POSITIVE LOGITS
    $-\
    0.67
    െയി
    0.65
     eigenvector
    0.62
     rejoicing
    0.62
     combating
    0.62
     jurid
    0.61
    ့
    0.59
    ostat
    0.59
    ുന്ന
    0.59
    回事
    0.59
    Activations Density 0.002%

    No Known Activations