© 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. 3003
    Prev
    Next
    INDEX
    Explanations

    times of crisis or difficulty

    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
     того
    0.64
     inception
    0.61
     allo
    0.61
    ע
    0.61
     aan
    0.60
     tratando
    0.59
    ️⃣
    0.58
    તાઓ
    0.58
    另一方面
    0.58
    症
    0.58
    POSITIVE LOGITS
    بە
    0.74
    iation
    0.70
    ேத்க
    0.67
     Тогда
    0.67
    ال
    0.66
    udarstvennyj
    0.65
    ো
    0.65
    ईआरटी
    0.65
    煉
    0.64
    б
    0.64
    Activations Density 0.023%

    No Known Activations