© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 11792
    Prev
    Next
    INDEX
    Explanations

    scientific or technical writing

    oai_token-act-pair · gemini-2.0-flash

    scientific language, chemistry

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     photolibrary
    -0.72
     NDEBUG
    -0.67
     *++
    -0.50
     Vim
    -0.50
     Vex
    -0.49
     deltaTime
    -0.49
     RISERV
    -0.48
     vegetative
    -0.48
     Joss
    -0.47
     electors
    -0.47
    POSITIVE LOGITS
    adaptiveStyles
    0.75
    chond
    0.66
    hydrogenase
    0.62
    microbial
    0.61
    uterine
    0.57
    morphism
    0.57
    väg
    0.57
    لينكات
    0.57
    eclamp
    0.56
    Viited
    0.56
    Activations Density 26.774%

    No Known Activations