© 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. 8613
    Prev
    Next
    INDEX
    Explanations

    capitalized words in the middle of a sentence along with mathematical and scientific notation, and also the word "in"

    oai_token-act-pair · gemini-2.0-flash

    scientific/technical texts

    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
    TagMode
    -0.63
    \{\\
    -0.59
    MemoryWarning
    -0.59
    ंदीखरीदारी
    -0.57
     propOrder
    -0.57
    Sklici
    -0.57
     gradova
    -0.56
    ruptedException
    -0.56
    WriteTagHelper
    -0.56
    GEBURTSDATUM
    -0.55
    POSITIVE LOGITS
    Sucesor
    0.67
    wpi
    0.52
     st
    0.51
    InputBorder
    0.49
    COUVER
    0.47
     Extragalactic
    0.47
     Talbot
    0.45
    prüche
    0.44
    argest
    0.44
     NOM
    0.44
    Activations Density 0.230%

    No Known Activations