© 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. 2862
    Prev
    Next
    INDEX
    Explanations

    newline and linebreak characters

    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
    1.53
    lc
    1.52
    ות
    1.46
    д
    1.45
    er
    1.39
    এছ
    1.38
     Vgl
    1.38
    деся
    1.36
    1.36
    ▫
    1.35
    POSITIVE LOGITS
     laget
    1.58
    жному
    1.50
     decisively
    1.50
    িকপ্ট
    1.46
     dynast
    1.46
    یف
    1.43
    𝘤
    1.43
    実は
    1.40
     kembali
    1.39
    धन
    1.39
    Activations Density 0.074%

    No Known Activations