© 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. 10939
    Prev
    Next
    INDEX
    Explanations

    code comments with parameter descriptions, especially those related to chart layouts and VPN sites

    oai_token-act-pair · gemini-2.0-flash

    to/of

    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
     صوتيه
    -0.55
    GOTREF
    -0.55
    
    -0.50
     متعلقه
    -0.47
    ://"
    -0.46
    archiviato
    -0.46
    dataTables
    -0.45
     useHistory
    -0.45
    InstanceState
    -0.44
     regular
    -0.43
    POSITIVE LOGITS
    verwijspagina
    0.81
     AssemblyCompany
    0.57
    niająca
    0.54
    }))
    0.54
    featureID
    0.54
    ември
    0.54
    configurable
    0.53
    Enders
    0.52
    queryInterface
    0.52
     observable
    0.51
    Activations Density 27.216%

    No Known Activations