© 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. 473
    Prev
    Next
    INDEX
    Explanations

    LaTeX math notation

    oai_token-act-pair · gemini-2.0-flash

    ampersand character

    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
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.84
     оригіналу
    -0.73
     TextAppearance
    -0.70
     }^{-
    -0.69
    Kjelder
    -0.68
     Shakspeare
    -0.68
    脚注の使い方
    -0.66
     Whigs
    -0.66
    󠁣
    -0.65
    PreferredItem
    -0.65
    POSITIVE LOGITS
    וויק
    0.48
    стреча
    0.46
    ungszeit
    0.45
    EXTERN
    0.44
     event
    0.43
    eradish
    0.43
    rakt
    0.42
    യി
    0.42
    enced
    0.42
     mine
    0.42
    Activations Density 1.801%

    No Known Activations