© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 4775
    Prev
    Next
    INDEX
    Explanations

    sarees or sari

    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
    inschaft
    2.69
    ן
    2.60
     싶
    2.57
    ו
    2.49
    hundred
    2.48
    udrait
    2.45
     blink
    2.43
    ضه
    2.34
    ب
    2.32
    রিদ্র
    2.29
    POSITIVE LOGITS
    م
    2.53
    てください
    2.49
    من
    2.48
    हे
    2.43
    el
    2.43
    et
    2.40
     größer
    2.40
    elapsed
    2.34
    pour
    2.28
     Оно
    2.26
    Activations Density 0.009%

    No Known Activations