© 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-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 11737
    Prev
    Next
    INDEX
    Explanations

    computer code snippets in PHP and related web technologies, and code structure like form states and handlers.

    oai_token-act-pair · gemini-2.0-flash

    Nationalities

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.54
     ***!
    -0.51
    Personensuche
    -0.49
     الحره
    -0.47
     beginnetje
    -0.47
    ⓧ
    -0.46
     @"/
    -0.46
    fjspx
    -0.45
    VolleyError
    -0.45
     مرئيه
    -0.45
    POSITIVE LOGITS
     brazilian
    0.84
     Brazilian
    0.75
     brazil
    0.72
     Argentine
    0.71
     Argent
    0.71
     portug
    0.69
    Brazilian
    0.69
     peruan
    0.68
     Chilean
    0.67
     Peruvian
    0.66
    Activations Density 21.885%

    No Known Activations