© 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. 8788
    Prev
    Next
    INDEX
    Explanations

    humanitarian -ism, -ization, -itarian, -ized

    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
    и
    1.87
    cellent
    1.84
    ক
    1.83
    ضی
    1.81
    ंग
    1.81
    ب
    1.80
    یدن
    1.79
     $<$
    1.79
    ۱۹
    1.76
     $*$
    1.75
    POSITIVE LOGITS
     startActivity
    2.24
     inp
    2.05
     möjlig
    2.03
    getActivity
    1.93
     extrapolated
    1.91
    𝓮
    1.91
     asper
    1.82
    とにかく
    1.82
    лә
    1.82
    荒
    1.80
    Activations Density 0.026%

    No Known Activations