© 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. 5599
    Prev
    Next
    INDEX
    Explanations

    numbers followed by hyphens, and the words "in" and "own."

    oai_token-act-pair · gemini-2.0-flash

    Time periods and scheduling

    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
    sizeCache
    -0.72
    __':
    -0.65
    Datuak
    -0.61
    ConstraintMaker
    -0.60
    UrlResolution
    -0.59
    MessageTagHelper
    -0.59
    PullParser
    -0.54
    AccessorTable
    -0.52
    RenderAtEndOf
    -0.52
    __':
    -0.50
    POSITIVE LOGITS
    MISSION
    0.55
    act
    0.54
     alba
    0.52
    GLFW
    0.50
     act
    0.50
     Ngo
    0.50
    ροφο
    0.49
    Климат
    0.49
     démarche
    0.48
     ory
    0.48
    Activations Density 13.616%

    No Known Activations