© 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. 5978
    Prev
    Next
    INDEX
    Explanations

    white space

    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
    ں
    2.46
     misdemean
    2.42
    во
    2.41
     rumin
    2.40
    Chúng
    2.35
    /−
    2.30
     повы
    2.29
     lectured
    2.29
     urgency
    2.28
    ណ៍
    2.28
    POSITIVE LOGITS
    ع
    2.66
    ें
    2.58
    ה
    2.55
    هم
    2.54
    ter
    2.46
    ters
    2.42
    ことです
    2.33
    a
    2.33
    ski
    2.25
    一个新的
    2.21
    Activations Density 0.015%

    No Known Activations