© 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. 7424
    Prev
    Next
    INDEX
    Explanations

    The neuron detects common suffixes or specific word endings

    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
    m
    2.82
    ن
    2.65
    zelfde
    2.52
    el
    2.50
    р
    2.48
    おそらく
    2.45
    र
    2.43
    ../
    2.36
    م
    2.35
    ли
    2.33
    POSITIVE LOGITS
    犸
    2.57
    ați
    2.45
    ̣n
    2.29
    šnje
    2.13
    ñez
    2.11
     digelar
    2.10
     privind
    2.10
     Presiden
    2.06
    django
    2.04
     dotyczą
    2.03
    Activations Density 0.031%

    No Known Activations