© 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. 6194
    Prev
    Next
    INDEX
    Explanations

    numerical values

    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
    i
    3.50
    ي
    2.94
    a
    2.85
    י
    2.65
    u
    2.57
    TAC
    2.42
    ธุ์
    2.33
    ા
    2.31
    л
    2.20
    ി
    2.19
    POSITIVE LOGITS
     expended
    2.47
    นอก
    2.40
    ্ড
    2.33
    tedir
    2.31
     inserir
    2.28
    ষ্ঠ
    2.27
    diethyl
    2.23
    ্ট
    2.20
     веще
    2.18
     nulla
    2.14
    Activations Density 0.027%

    No Known Activations