© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 310
    Prev
    Next
    INDEX
    Explanations

    is focused on the use of online accounts, especially for social media or finance, possibly with a negative connotation

    oai_token-act-pair · gemini-2.0-flash

    account

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     account
    -2.66
     accounts
    -2.36
    account
    -2.30
     Account
    -2.28
    Account
    -2.16
     Accounts
    -2.06
    accounts
    -2.06
     ACCOUNT
    -2.00
    Accounts
    -1.95
    ACCOUNT
    -1.77
    POSITIVE LOGITS
    TagMode
    0.84
    RegressionTest
    0.82
    出版年
    0.81
    tonsoft
    0.73
    RetentionPolicy
    0.70
    MENAFN
    0.66
     مرئيه
    0.65
     оригіналу
    0.65
     Reverso
    0.63
    redient
    0.63
    Activations Density 4.905%

    No Known Activations