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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7106
    Prev
    Next
    INDEX
    Explanations

    references to surveys and studies, especially those involving data collection on adults

    oai_token-act-pair · gemini-2.0-flash

    Polls and statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     ?>">
    -0.54
    orna
    -0.50
    oole
    -0.50
    Framebuffer
    -0.49
     peninsula
    -0.47
    évaluateur
    -0.47
    Tikang
    -0.46
     JADX
    -0.46
    code
    -0.46
     nî
    -0.45
    POSITIVE LOGITS
    posedge
    0.57
    CascadeType
    0.57
    ="@+
    0.56
     actualité
    0.56
    ViewImports
    0.54
    .*")]
    0.54
     maî
    0.54
    IGraphics
    0.53
    Numerology
    0.53
    Spoilers
    0.51
    Activations Density 7.242%

    No Known Activations