© 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. 2-GEMMASCOPE-2-TRANSCODER-16K
    7. 1154
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
    ">(</
    2.85
    ">)</
    2.81
    documented
    2.63
    ﺎ
    2.62
    ا
    2.60
     tetap
    2.55
     soothe
    2.53
    UMENT
    2.51
    TAIN
    2.46
    textbackslash
    2.44
    POSITIVE LOGITS
    р
    2.81
    в
    2.64
    راب
    2.62
    電話
    2.45
    别的
    2.41
     enfin
    2.33
     pertenec
    2.31
    ])));
    2.23
    েন্দ্রলাল
    2.23
    मे
    2.17
    Activations Density 0.012%

    No Known Activations