© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15486
    Prev
    Next
    INDEX
    Explanations

    a mixed bag of equation symbols, dashes, and single quotes/parentheses in what looks like computer code, often next to other non-alphanumeric characters

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash

    hyphen

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
    ic
    -0.57
    ization
    -0.56
    iat
    -0.55
    ibis
    -0.55
    i
    -0.55
    its
    -0.54
    ised
    -0.54
    ich
    -0.54
    ire
    -0.53
    ising
    -0.53
    POSITIVE LOGITS
    oa̍t
    0.65
    urlpatterns
    0.59
    more
    0.58
    webElementXpaths
    0.55
    MORE
    0.52
    emde
    0.49
    ValueStyle
    0.49
    erweise
    0.48
    en
    0.44
    useState
    0.44
    Activations Density 11.353%

    No Known Activations