© 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. 8044
    Prev
    Next
    INDEX
    Explanations

    nuclear energy and physics concepts

    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
    ू
    2.52
     wits
    2.39
    Damn
    2.37
    \,
    2.34
     lack
    2.31
     stir
    2.29
     dictate
    2.23
    \,.
    2.21
    mck
    2.20
    atthaya
    2.15
    POSITIVE LOGITS
    础
    2.56
     somehow
    2.30
     distint
    2.30
    are
    2.09
    startDate
    2.06
    붉
    2.04
    ња
    2.02
    संधान
    2.02
    jest
    2.01
    علم
    2.00
    Activations Density 0.073%

    No Known Activations