© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 3261
    Prev
    Next
    INDEX
    Explanations

    words that are common stopwords in mathematical writing

    oai_token-act-pair · gemini-2.0-flash

    Math/CS papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    WriteBarrier
    -0.81
     "..\..\..\
    -0.78
     autorytatywna
    -0.76
     lenker
    -0.75
     nakalista
    -0.74
    Vidite
    -0.73
     >=",
    -0.73
    Personendaten
    -0.70
     "..\..\
    -0.68
    awtextra
    -0.66
    POSITIVE LOGITS
     conc
    0.50
     a
    0.47
     executive
    0.47
     organic
    0.47
     edges
    0.44
     all
    0.44
     course
    0.44
    Campe
    0.44
    dit
    0.44
    ontas
    0.43
    Activations Density 11.762%

    No Known Activations