© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7814
    Prev
    Next
    INDEX
    Explanations

    the word "related", as well as words with the suffix "tion" and some words related to dating, with some false positives

    oai_token-act-pair · gemini-2.0-flash

    related

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     related
    -2.50
    related
    -2.27
     Related
    -2.16
    Related
    -2.14
    <bos>
    -1.86
     RELATED
    -1.78
    RELATED
    -1.49
     relate
    -1.47
     relacionado
    -1.43
     relating
    -1.38
    POSITIVE LOGITS
     NgModule
    0.72
     AssemblyCulture
    0.66
     NSCoder
    0.65
     TestBed
    0.64
     AppCompatTheme
    0.60
    criptive
    0.56
    Hasta
    0.56
    </tfoot>
    0.56
    setContentView
    0.55
    BrowserRouter
    0.55
    Activations Density 2.115%

    No Known Activations