© 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. 13413
    Prev
    Next
    INDEX
    Explanations

    references to Stack Overflow and other Stack Exchange sites or the word "fault".

    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
    Negative Logits
     of
    -0.49
     free
    -0.47
     about
    -0.43
     es
    -0.41
    acy
    -0.40
    dr
    -0.39
    NoSuchAlgorithm
    -0.39
    ou
    -0.38
     at
    -0.38
     Dr
    -0.38
    POSITIVE LOGITS
    saraba
    1.10
    Personensuche
    1.04
    MigrationBuilder
    0.99
    RTEE
    0.96
     مشين
    0.96
    contentLoaded
    0.93
    ########.
    0.92
     Exacts
    0.91
    UnusedPrivate
    0.90
    Vidite
    0.88
    Activations Density 1.709%

    No Known Activations