© 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
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 16018
    Prev
    Next
    INDEX
    Explanations

    superscripted prime symbols and related characters possibly found in math papers

    oai_token-act-pair · gemini-2.0-flash

    math

    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
     kaarangay
    -1.27
     nakalista
    -1.11
     betweenstory
    -1.05
    PMailer
    -1.02
    AddTagHelper
    -1.02
     resourceCulture
    -1.00
     مشين
    -0.97
    Carriera
    -0.94
     Roskov
    -0.93
     متعلقه
    -0.90
    POSITIVE LOGITS
    *
    0.62
    /
    0.57
    (
    0.52
    ,
    0.46
     *
    0.45
     }
    0.45
    top
    0.45
    -
    0.43
    ('
    0.43
    [
    0.43
    Activations Density 3.302%

    No Known Activations