© 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
    2. Gemma-2-2B
    3. 24-GEMMASCOPE-TRANSCODER-16K
    4. 310
    Prev
    Next
    INDEX
    Explanations

    months and years

    oai_token-act-pair · gemini-2.0-flash

    Months

    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
     ghost
    -1.30
     Halloween
    -1.25
    Halloween
    -1.23
     spooky
    -1.20
     halloween
    -1.20
     pumpkin
    -1.19
     September
    -1.18
    halloween
    -1.16
     October
    -1.15
     Ghost
    -1.15
    POSITIVE LOGITS
    SequentialGroup
    0.54
     himo
    0.48
     Codable
    0.48
    asticity
    0.48
    SaveChangesAsync
    0.47
    DockStyle
    0.47
    RegistryLite
    0.47
    ButtonStyle
    0.46
    HasAnnotation
    0.46
     pregi
    0.46
    Activations Density 1.471%

    No Known Activations