© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9499
    Prev
    Next
    INDEX
    Explanations

    words that indicate judgment, opinion, or explanation.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    脚注の使い方
    -0.71
    Diweddarwch
    -0.65
     تضيفلها
    -0.64
    seamnă
    -0.62
    stdc
    -0.59
     оригіналу
    -0.59
    endpush
    -0.58
     OFDb
    -0.58
    ipedi
    -0.57
    SPATH
    -0.57
    POSITIVE LOGITS
    addPreferredGap
    0.51
     later
    0.46
     aé
    0.45
    skyl
    0.45
    kom
    0.44
    MSS
    0.44
     they
    0.44
     pourrez
    0.43
     dor
    0.43
    FileDialog
    0.43
    Activations Density 3.933%

    No Known Activations