© 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. 5944
    Prev
    Next
    INDEX
    Explanations

    menu bar

    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
    й
    3.41
     eben
    2.51
    Grunge
    2.41
    _{
    2.26
    𝘆
    2.25
    दान
    2.21
    ف
    2.20
    𝐲
    2.19
     complied
    2.19
    事情
    2.18
    POSITIVE LOGITS
    ت
    3.19
    t
    3.12
    ل
    3.09
    т
    3.04
    ης
    2.91
    ট
    2.88
    sü
    2.64
    ਵ
    2.62
    تهم
    2.61
    挞
    2.61
    Activations Density 0.006%

    No Known Activations