© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13149
    Prev
    Next
    INDEX
    Explanations

    parts of Java programming language code

    oai_token-act-pair · gemini-2.0-flash

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    <bos>
    -1.45
     EconPapers
    -0.63
    AnchorStyles
    -0.63
     становника
    -0.58
     Савезне
    -0.57
    DockStyle
    -0.54
    sizeCache
    -0.53
    RegressionTest
    -0.52
    engager
    -0.51
    webElementXpaths
    -0.51
    POSITIVE LOGITS
    ToProps
    0.67
     ―――――
    0.65
     Theſe
    0.65
     Beſ
    0.64
     ――――――――
    0.63
    StateToProps
    0.61
    tôi
    0.61
     Efq
    0.59
    Atsauces
    0.59
     combineReducers
    0.59
    Activations Density 1.645%

    No Known Activations