© 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
    2. Gemma-3-4B-IT
    3. 3-GEMMASCOPE-2-TRANSCODER-262K
    4. 4670
    Prev
    Next
    INDEX
    Explanations

    string literals and code delimiters

    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
    ي
    3.32
    ie
    2.95
    শন
    2.93
    на
    2.91
    ோ
    2.90
     estoppel
    2.87
     dint
    2.78
     thirds
    2.74
    unpublished
    2.66
     implication
    2.61
    POSITIVE LOGITS
    𝙧
    2.99
    𝙮
    2.95
    고
    2.89
    з
    2.80
    𝕐
    2.72
    ści
    2.65
    y
    2.65
     سته
    2.58
    ^{
    2.55
     всего
    2.52
    Activations Density 0.020%

    No Known Activations