© 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. 5955
    Prev
    Next
    INDEX
    Explanations

    summarizing the key differences

    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
    \|$
    3.96
    ​]]
    3.91
    Hej
    3.87
    िक
    3.37
    ラクマ
    3.19
    +|
    3.14
    (|
    3.03
    \|
    3.01
     सितम्बर
    2.98
    particular
    2.97
    POSITIVE LOGITS
    د
    3.94
    ر
    3.39
    ses
    3.36
    ding
    3.26
    ت
    3.01
    ер
    2.95
    𝚋
    2.92
    𝑖
    2.85
    sing
    2.85
    دون
    2.81
    Activations Density 0.100%

    No Known Activations