© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6911
    Prev
    Next
    INDEX
    Explanations

    tired of

    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
     शही
    2.34
    ڈ
    2.29
    ниц
    2.29
     endDate
    2.28
    vents
    2.26
    িল্প
    2.26
    ার্ড
    2.23
     ক্ষেত্রে
    2.17
     eher
    2.15
    sliced
    2.13
    POSITIVE LOGITS
    ت
    2.73
    ल
    2.38
    le
    2.33
    弃
    2.31
    леп
    2.16
    loving
    2.10
    ly
    2.02
    t
    2.00
    ़
    1.93
    tod
    1.91
    Activations Density 0.015%

    No Known Activations