© 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. 6930
    Prev
    Next
    INDEX
    Explanations

    a variety of keywords, including those related to medicine, programming, physics, and job postings.

    oai_token-act-pair · gemini-2.0-flash

    say "e" words

    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
    Geplaatst
    -0.75
    DockStyle
    -0.67
    HideFlags
    -0.64
     kasarigan
    -0.61
    tonode
    -0.59
    ItemBackground
    -0.59
    queryInterface
    -0.59
    InitVars
    -0.58
    HasAnnotation
    -0.57
     typelib
    -0.57
    POSITIVE LOGITS
     e
    0.93
     es
    0.76
     er
    0.73
     е
    0.72
     ed
    0.68
     ef
    0.61
     э
    0.60
     ɛ
    0.60
     eb
    0.60
    のエ
    0.59
    Activations Density 7.327%

    No Known Activations