© 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. 7633
    Prev
    Next
    INDEX
    Explanations

    Here's a

    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
    l
    2.77
    zelfde
    2.56
    lado
    2.45
    leased
    2.37
    们
    2.36
    ০
    2.36
    ्रांत
    2.33
    er
    2.30
    en
    2.27
    oare
    2.25
    POSITIVE LOGITS
     regards
    2.15
    መሳሳይ
    2.14
    পূর্ব
    2.14
    ጨማሪ
    2.14
     불구하고
    1.94
    զ
    1.92
     truncated
    1.92
     regard
    1.88
    ✫
    1.87
     pitfalls
    1.83
    Activations Density 0.305%

    No Known Activations