© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14474
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to manufacturing, surface coatings, and chemical properties, sometimes including part numbers

    oai_token-act-pair · gemini-2.0-flash

    coatings and manufacturing

    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
    ьаж
    -0.57
     Roskov
    -0.56
    webElementGuid
    -0.50
     kasarigan
    -0.45
     estekak
    -0.45
     Centa
    -0.43
    ChildScrollView
    -0.43
    TemporalType
    -0.43
    Autoritní
    -0.43
    arcoma
    -0.42
    POSITIVE LOGITS
    onViewCreated
    0.69
    
    0.66
    sqcup
    0.57
    webtoken
    0.53
    DebuggerNonUser
    0.53
     وتسجيلات
    0.52
     désolés
    0.52
     optic
    0.52
     fabriquer
    0.51
    onHide
    0.51
    Activations Density 11.402%

    No Known Activations