© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12217
    Prev
    Next
    INDEX
    Explanations

    formatting lines in a text document

    oai_token-act-pair · gemini-2.0-flash

    "see also" links

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     xmm
    -0.53
    seku
    -0.51
     Epile
    -0.51
     démoc
    -0.50
     batsman
    -0.49
    withIdentifier
    -0.49
     Seif
    -0.48
    tableFuture
    -0.48
     publick
    -0.48
     AtomicInteger
    -0.47
    POSITIVE LOGITS
    OGND
    0.79
    UserScript
    0.70
    fjspx
    0.60
    tiennent
    0.58
    geber
    0.56
    łowa
    0.53
     lenker
    0.53
     helft
    0.53
    <bos>
    0.52
     GenerationType
    0.51
    Activations Density 1.246%

    No Known Activations