© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 4600
    Prev
    Next
    INDEX
    Explanations

    names of research programs, institutions, and organizational units

    oai_token-act-pair · gemini-2.0-flash

    organizations and institutions

    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
     ángel
    -0.40
    войства
    -0.37
     glabrous
    -0.37
     anjo
    -0.37
    Bitch
    -0.35
     beets
    -0.35
    Stepper
    -0.35
    好吃
    -0.35
     clogs
    -0.34
     určit
    -0.34
    POSITIVE LOGITS
    клопе
    0.72
    migrationBuilder
    0.67
     iconFacebook
    0.65
    kå
    0.61
    makeConstraints
    0.60
     AppModule
    0.60
    )"),
    0.59
    ">/
    0.57
     *)__
    0.57
    )»
    0.56
    Activations Density 13.728%

    No Known Activations