© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 3212
    Prev
    Next
    INDEX
    Explanations

    explanatory or concluding particles

    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_5_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
    িয়া
    0.71
     Crimea
    0.69
    แหน่ง
    0.69
     informacija
    0.69
    mér
    0.68
    ি
    0.68
    ی
    0.66
     Calf
    0.66
     majesty
    0.66
     Macedonia
    0.65
    POSITIVE LOGITS
    toEqual
    0.80
    tt
    0.59
    el
    0.59
    Damn
    0.59
    tones
    0.58
    Dong
    0.58
    루
    0.57
    damn
    0.55
    ></
    0.55
    SLC
    0.55
    Activations Density 0.001%

    No Known Activations