© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6681
    Prev
    Next
    INDEX
    Explanations

    words denoting importance or position

    oai_token-act-pair · gemini-2.0-flash

    location/positioning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     TAMBÉM
    -0.53
    !
    -0.53
     outbreak
    -0.52
    an
    -0.52
     accounts
    -0.50
    ?
    -0.49
    c
    -0.47
    Topping
    -0.47
    ↵
    -0.47
    u
    -0.47
    POSITIVE LOGITS
    DockStyle
    1.22
    IntoConstraints
    1.17
     CURIAM
    1.02
    
    0.98
    +#+#
    0.98
    ."</
    0.94
     propOrder
    0.94
    migrationBuilder
    0.94
    kuuta
    0.93
    AnchorStyles
    0.92
    Activations Density 0.468%

    No Known Activations