© 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. 8506
    Prev
    Next
    INDEX
    Explanations

    titles of books and literary works

    oai_token-act-pair · gemini-2.0-flash

    titles

    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
    脚注の使い方
    -0.73
    ChildScrollView
    -0.69
    RegressionTest
    -0.60
    AnchorStyles
    -0.59
    Personendaten
    -0.58
    tagHelperRunner
    -0.57
    InjectAttribute
    -0.55
    riezmann
    -0.54
    verifyException
    -0.51
    MOQ
    -0.50
    POSITIVE LOGITS
     Revealed
    0.61
     Beneath
    0.60
     Across
    0.60
     Discovered
    0.60
     as
    0.59
     Throughout
    0.57
     denies
    0.57
     Through
    0.57
     Around
    0.55
     Drawn
    0.54
    Activations Density 7.331%

    No Known Activations