© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1251
    Prev
    Next
    INDEX
    Explanations

    symbols and words related to math, programming, or finance, sometimes occurring in a sequence

    oai_token-act-pair · gemini-2.0-flash

    Code and equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     MM
    -1.30
     Me
    -1.18
     Mi
    -1.17
    MM
    -1.17
     M
    -1.17
     Min
    -1.14
     Mo
    -1.13
     MU
    -1.12
     Ма
    -1.12
     Ma
    -1.12
    POSITIVE LOGITS
    abestanden
    0.52
    Hochspringen
    0.47
     disponibilités
    0.46
    IVEREF
    0.46
     Савезне
    0.43
    AddTagHelper
    0.42
    ibut
    0.42
     Croce
    0.41
    yled
    0.40
    ंदीखरीदारी
    0.38
    Activations Density 48.824%

    No Known Activations