© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 256
    Prev
    Next
    INDEX
    Explanations

    text contained within LaTeX math environments

    oai_token-act-pair · gemini-2.0-flash

    mathematical equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     kaarangay
    -0.71
    الإنجليزية
    -0.69
    (!__
    -0.59
     <=",
    -0.59
     noDo
    -0.56
    GraphicsUnit
    -0.56
    ########.
    -0.56
     OMITBAD
    -0.56
    execSQL
    -0.55
    __*/
    -0.54
    POSITIVE LOGITS
    aritions
    0.52
     ẩm
    0.46
    himo
    0.45
    RoutingModule
    0.45
     base
    0.45
    сшта
    0.44
    BasePath
    0.44
    shadowRadius
    0.43
     sum
    0.42
     jöv
    0.42
    Activations Density 27.908%

    No Known Activations