© 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
    2. Gemma-2-2B
    3. 3-GEMMASCOPE-TRANSCODER-16K
    4. 9198
    Prev
    Next
    INDEX
    Explanations

    prepositions and pronouns, as well as the french words "du" and "des"

    oai_token-act-pair · gemini-2.0-flash

    likely foreign, legal texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ásban
    -0.50
     crotch
    -0.45
    +#+#
    -0.45
     démocr
    -0.45
     armp
    -0.44
    UnsafeEnabled
    -0.44
    asymp
    -0.44
     rechange
    -0.43
     gotas
    -0.43
    ngths
    -0.42
    POSITIVE LOGITS
    ThroughAttribute
    0.83
    verwijspagina
    0.67
     Waray
    0.67
    ρών
    0.63
    initComponents
    0.63
    <bos>
    0.61
    enderror
    0.60
    /−
    0.60
     ffilmiau
    0.60
     متعلقه
    0.59
    Activations Density 0.759%

    No Known Activations