© 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
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 3358
    Prev
    Next
    INDEX
    Explanations

    technical writing, frequently relating to chemistry processes, including mentions of elements/compounds, methods, materials, and techniques.

    oai_token-act-pair · gemini-2.0-flash

    Chemical/technical terms

    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
    ConstraintMaker
    -0.68
     CreateTagHelper
    -0.54
    LLocation
    -0.52
     فريبيس
    -0.51
    tableFuture
    -0.49
     esternos
    -0.49
    ьаж
    -0.49
    IInterface
    -0.48
    ++]=
    -0.47
    (!__
    -0.46
    POSITIVE LOGITS
    Xaml
    0.59
     sulphuric
    0.58
     resourceCulture
    0.57
    AndroidJUnit
    0.57
     vulgaires
    0.57
     sulfuric
    0.55
    JvmStatic
    0.54
    Browsable
    0.52
    zepam
    0.52
    CppCodeGen
    0.52
    Activations Density 26.649%

    No Known Activations