© 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. 11952
    Prev
    Next
    INDEX
    Explanations

    code snippets with file permissions

    oai_token-act-pair · gemini-2.0-flash

    file permissions

    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
    SharedCtor
    -0.57
    fjspx
    -0.52
    Sklici
    -0.47
     kog
    -0.46
     iArr
    -0.45
    Atsauces
    -0.45
    appré
    -0.44
    uken
    -0.44
     Bug
    -0.44
    DIPSETTING
    -0.44
    POSITIVE LOGITS
    IsContent
    0.71
    
    0.69
    WriteTagHelper
    0.69
    makeConstraints
    0.68
     AttributeSet
    0.62
    Personendaten
    0.61
    AccessFile
    0.61
    CloseOperation
    0.61
    TypedDataSet
    0.57
     AssemblyTitle
    0.57
    Activations Density 1.220%

    No Known Activations