© 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. 7134
    Prev
    Next
    INDEX
    Explanations

    conservation of energy/momentum

    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
    ка
    3.31
    요
    2.78
    how
    2.73
    ان
    2.70
    лү
    2.58
    توان
    2.58
     tunable
    2.56
    Ä
    2.54
     وسهلا
    2.54
    либо
    2.53
    POSITIVE LOGITS
     overheard
    2.86
     plasmids
    2.74
    ifornia
    2.66
    Incidentally
    2.62
    त्मक
    2.58
     kip
    2.52
     juices
    2.49
     वहीं
    2.48
    =============
    2.47
    Pokémon
    2.46
    Activations Density 0.081%

    No Known Activations