© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9058
    Prev
    Next
    INDEX
    Explanations

    context related to mathematical proofs and theorems

    oai_token-act-pair · gemini-2.0-flash

    case

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ReusableCell
    -1.00
    GEBURTSDATUM
    -0.99
     disambiguazione
    -0.96
     صوتيه
    -0.95
    ########.
    -0.93
     يتيمه
    -0.91
     Exacts
    -0.91
    styleType
    -0.90
    __(/*!
    -0.89
    ioutil
    -0.88
    POSITIVE LOGITS
    <bos>
    1.41
    '
    0.73
    ’
    0.65
    ↵
    0.57
     
    0.57
     at
    0.56
    se
    0.54
    0
    0.54
    1
    0.52
    (
    0.52
    Activations Density 3.362%

    No Known Activations