© 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. 2535
    Prev
    Next
    INDEX
    Explanations

    code snippets using temperature and heater variables, with branches for possible temperature values

    oai_token-act-pair · gemini-2.0-flash

    Scientific/technical discussions

    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
     He
    -2.27
    He
    -2.25
    he
    -2.20
     he
    -2.05
     HE
    -1.98
    HE
    -1.94
     She
    -1.91
    she
    -1.87
    She
    -1.86
     SHE
    -1.60
    POSITIVE LOGITS
    ItemBackground
    0.66
    nocache
    0.62
    IndentedString
    0.60
    ]")]
    0.57
     LoggerFactory
    0.57
     HasFactory
    0.56
    addCriterion
    0.56
    AlterField
    0.52
    Manbalar
    0.52
    Salvador
    0.52
    Activations Density 2.610%

    No Known Activations