© 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. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5302
    Prev
    Next
    INDEX
    Explanations

    collocations of prepositions and place names, especially in the context of sports.

    oai_token-act-pair · gemini-2.0-flash

    programming syntax elements

    np_token-act-pair-logits · gpt-4o-mini

    locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     الحره
    -0.54
     factory
    -0.52
    DrawerToggle
    -0.51
    TagMode
    -0.48
     functional
    -0.47
     Functional
    -0.46
    Functional
    -0.45
     intStringLen
    -0.45
    raszamy
    -0.45
    VIAF
    -0.45
    POSITIVE LOGITS
    "}")
    0.65
    ISupport
    0.63
    __":
    0.62
    MetaObject
    0.60
    DebuggerStep
    0.58
    strptime
    0.58
    __":
    
    0.58
    ")->
    0.57
    Personendaten
    0.56
    afone
    0.56
    Activations Density 1.559%

    No Known Activations