© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11723
    Prev
    Next
    INDEX
    Explanations

    extract information related to mathematical equations and character descriptions, especially those occurring with personal identifiers or roles.

    oai_token-act-pair · gemini-2.0-flash

    transformations

    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
     ISNI
    -0.60
    σθαι
    -0.58
     phases
    -0.57
    ênis
    -0.56
    Revenir
    -0.55
     myrtle
    -0.54
     Phases
    -0.54
    SEGUIR
    -0.54
    izarse
    -0.54
    ônus
    -0.52
    POSITIVE LOGITS
    хьтан
    0.65
     defaultstate
    0.64
     nahilalakip
    0.62
    initComponents
    0.59
    ItemBackground
    0.57
     calendriers
    0.52
    ActivityCompat
    0.52
     esternos
    0.52
    RenderAtEndOf
    0.51
     invokingState
    0.48
    Activations Density 2.197%

    No Known Activations