© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11973
    Prev
    Next
    INDEX
    Explanations

    mentions of tech companies and products, especially in the mobile device market

    oai_token-act-pair · gemini-2.0-flash

    ered

    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
    RegressionTest
    -0.55
    thâu
    -0.51
     ohnehin
    -0.50
    ̣n
    -0.49
    Datuak
    -0.48
    ucle
    -0.47
    ệc
    -0.47
    inguém
    -0.46
     تكبرها
    -0.46
    ostom
    -0.45
    POSITIVE LOGITS
    TypedDataSet
    0.79
     Theſe
    0.56
    ArgsConstructor
    0.56
     FetchType
    0.52
     Monfieur
    0.51
    :+:
    0.50
    AutoField
    0.48
    @[+][
    0.48
    BagConstraints
    0.48
     nahilalakip
    0.48
    Activations Density 3.562%

    No Known Activations