© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6541
    Prev
    Next
    INDEX
    Explanations

    addresses

    oai_token-act-pair · gemini-2.0-flash

    addresses and streets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    WriteTagHelper
    -0.89
     ModelExpression
    -0.84
    MigrationBuilder
    -0.83
    AddTagHelper
    -0.80
    rungsseite
    -0.79
    
    -0.78
     AssemblyCulture
    -0.72
    ----</
    -0.71
    WebElementEntity
    -0.70
     doInBackground
    -0.70
    POSITIVE LOGITS
    amin
    0.50
     Companion
    0.47
     Neben
    0.46
     Foer
    0.45
    ATURE
    0.45
     Partner
    0.44
     Bel
    0.44
    guten
    0.43
     companion
    0.43
     fol
    0.43
    Activations Density 1.475%

    No Known Activations