© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 8730
    Prev
    Next
    INDEX
    Explanations

    reading about

    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
    ıyla
    2.42
    جلس
    2.41
    स
    2.33
    ला
    2.32
     এটাও
    2.32
    ا
    2.31
    ına
    2.18
     Workout
    2.17
     entend
    2.15
    สรร
    2.15
    POSITIVE LOGITS
    ীয়
    2.35
     سینٹی
    2.31
     вопроса
    2.28
    ू
    2.27
    ευ
    2.18
    িকপ্ট
    2.17
     hollow
    2.15
    ر
    2.13
    iteten
    2.12
     блоков
    2.10
    Activations Density 0.010%

    No Known Activations