© 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. 12-GEMMASCOPE-TRANSCODER-16K
    4. 11850
    Prev
    Next
    INDEX
    Explanations

    references to external data sources within a scientific paper

    oai_token-act-pair · gemini-2.0-flash

    online

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    +#+#
    -0.76
    InstrumentedTest
    -0.73
    PostExecute
    -0.71
    WindowConstants
    -0.68
    XmlEnum
    -0.68
    IBOutlet
    -0.67
     resourceCulture
    -0.67
    ngOnInit
    -0.67
    erialized
    -0.66
     BoxFit
    -0.65
    POSITIVE LOGITS
    code
    0.46
     code
    0.45
     betweenstory
    0.44
    Code
    0.44
    dighet
    0.42
     more
    0.41
     Code
    0.39
    CODE
    0.39
     CODE
    0.38
    abilité
    0.38
    Activations Density 0.482%

    No Known Activations