© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3149
    Prev
    Next
    INDEX
    Explanations

    Mahi Central University 6 months

    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_5_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
    
    1.83
    𝑠
    1.68
    ᥒ
    1.64
    级别的
    1.63
    ности
    1.63
    ल्ड
    1.61
     Fairness
    1.60
    শনাল
    1.60
     maxWidth
    1.59
    ɖ
    1.58
    POSITIVE LOGITS
    ين
    2.39
     reta
    1.93
     hele
    1.93
     всего
    1.92
     konc
    1.86
     messo
    1.86
    <bos>
    1.83
     queued
    1.83
     duplic
    1.83
     certe
    1.81
    Activations Density 0.000%

    No Known Activations