© 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. 7029
    Prev
    Next
    INDEX
    Explanations

    letters and numbers

    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
    nment
    0.84
     volte
    0.82
     alia
    0.82
     eğer
    0.81
    們
    0.81
     fiind
    0.78
     fie
    0.78
     ressort
    0.76
    spur
    0.76
     Конечно
    0.75
    POSITIVE LOGITS
    그
    0.97
    ))$.
    0.90
    S
    0.88
    ള്‍
    0.87
    ۾
    0.87
    থেষ্ট
    0.87
     ihe
    0.87
    )=$
    0.86
    Naming
    0.85
    knife
    0.85
    Activations Density 0.014%

    No Known Activations