Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14532
    Prev
    Next
    INDEX
    Explanations

    math problems.

    oai_token-act-pair · gemini-2.0-flash

    call

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     Roskov
    -0.95
     nahilalakip
    -0.93
    queryInterface
    -0.89
    findpost
    -0.89
    Personendaten
    -0.88
    onViewCreated
    -0.87
     AssemblyVersion
    -0.86
    IntoConstraints
    -0.86
     Normdatei
    -0.84
    
    -0.84
    POSITIVE LOGITS
     composition
    0.70
     Call
    0.68
    Call
    0.65
     call
    0.63
    circ
    0.63
    composition
    0.59
     compose
    0.58
     composta
    0.58
     compositions
    0.58
    call
    0.57
    Activations Density 3.494%

    No Known Activations