© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 8308
    Prev
    Next
    INDEX
    Explanations

    the French words "il", "y", "je", and related pronouns and auxiliary verbs

    oai_token-act-pair · gemini-2.0-flash

    il

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    jooq
    -0.55
    viewDidLoad
    -0.54
    phalt
    -0.52
    urlencoded
    -0.51
    didSet
    -0.50
    脚注の使い方
    -0.50
     bulunabilir
    -0.50
    waitKey
    -0.50
    onedDateTime
    -0.50
     Constitucional
    -0.49
    POSITIVE LOGITS
    tamol
    0.64
    $_['
    0.53
     abri
    0.53
    ://"
    0.52
    ://
    0.50
    Legenda
    0.50
     myſelf
    0.49
    AndEndTag
    0.49
    Aholisi
    0.49
     Exacts
    0.49
    Activations Density 2.957%

    No Known Activations