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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4911
    Prev
    Next
    INDEX
    Explanations

    words in French, especially pronouns, articles, and possessive adjectives

    oai_token-act-pair · gemini-2.0-flash

    les

    np_max-act · gemini-2.0-flash

    les

    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_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
    Geplaatst
    -0.80
     les
    -0.73
    <bos>
    -0.69
     telefónica
    -0.68
    AccessorTable
    -0.67
     ioutil
    -0.65
    таратура
    -0.65
     Combien
    -0.65
    fetchall
    -0.64
    ("")]
    -0.64
    POSITIVE LOGITS
    DataAnnotations
    0.50
    Hentet
    0.47
    createClass
    0.46
    lorus
    0.45
    breviated
    0.43
    :+:
    0.43
     parent
    0.42
    hna
    0.42
    =\""
    0.42
    parente
    0.41
    Activations Density 2.349%

    No Known Activations