© 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. 8337
    Prev
    Next
    INDEX
    Explanations

    text giving instructions for creative assignments

    oai_token-act-pair · gemini-2.0-flash

    Lesson plans and instructions

    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
    CodeAttribute
    -0.81
     NDL
    -0.77
    mybatisplus
    -0.76
     disambiguazione
    -0.72
     ujednoznacz
    -0.71
     Audiodateien
    -0.68
    LayoutStyle
    -0.67
     createSprite
    -0.66
    脚注の使い方
    -0.66
     Normdatei
    -0.65
    POSITIVE LOGITS
    الصفحه
    0.50
     BoxFit
    0.45
    WEBPACK
    0.40
    Autriche
    0.39
    ILog
    0.39
     Zwiebel
    0.39
    elni
    0.39
     Susana
    0.38
     restaurantes
    0.38
    openha
    0.38
    Activations Density 1.628%

    No Known Activations