© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5653
    Prev
    Next
    INDEX
    Explanations

    place names or references to geographic regions

    oai_token-act-pair · gemini-2.0-flash

    Finland

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    EDEFAULT
    -0.98
    parsedMessage
    -0.93
    MigrationBuilder
    -0.85
    rungsseite
    -0.84
    jspx
    -0.82
     disambiguazione
    -0.81
    MemoryWarning
    -0.80
    AlterField
    -0.80
     CreateTagHelper
    -0.80
     initComponents
    -0.79
    POSITIVE LOGITS
     thuận
    0.41
    koll
    0.41
    jaan
    0.36
     R
    0.33
     situasi
    0.32
     sicheren
    0.32
     rând
    0.32
     cœurs
    0.31
    kat
    0.31
    hold
    0.31
    Activations Density 0.431%

    No Known Activations