© 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. 8259
    Prev
    Next
    INDEX
    Explanations

    descriptive words related to physical spaces and events.

    oai_token-act-pair · gemini-2.0-flash

    locations/placement

    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
    OGND
    -0.77
     EconPapers
    -0.66
    UrlResolution
    -0.66
     "..\..\
    -0.61
    addPreferredGap
    -0.59
     noqa
    -0.59
     AssemblyTitle
    -0.57
     iconFacebook
    -0.57
    Espèce
    -0.54
     /\.
    -0.54
    POSITIVE LOGITS
     SPRINGS
    0.55
     art
    0.51
     lake
    0.50
     lawn
    0.50
    olon
    0.49
     lakes
    0.49
     pool
    0.48
    EndProject
    0.47
     coral
    0.46
     cohe
    0.46
    Activations Density 3.108%

    No Known Activations