© 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. 9482
    Prev
    Next
    INDEX
    Explanations

    emotional and physical descriptions of people

    oai_token-act-pair · gemini-2.0-flash

    physical appearance

    np_max-act · 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
    <bos>
    -0.78
     ujednoznacz
    -0.64
    Hauptartikel
    -0.60
     invokingState
    -0.48
    subpackage
    -0.48
    phans
    -0.48
     propOrder
    -0.47
    Fordítás
    -0.47
    engeti
    -0.46
    avits
    -0.46
    POSITIVE LOGITS
    runApp
    0.61
    IntoConstraints
    0.59
    TestingModule
    0.58
     doInBackground
    0.57
     commerciali
    0.54
     onPostExecute
    0.52
    tagHelperRunner
    0.52
    CodedInputStream
    0.52
    SharedDtor
    0.50
     potere
    0.50
    Activations Density 0.519%

    No Known Activations