© 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. 7808
    Prev
    Next
    INDEX
    Explanations

    references to political and military events, parties and organizations, especially when associated with location and timeline.

    oai_token-act-pair · gemini-2.0-flash

    Government and politics

    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
    RegressionTest
    -0.79
    complexContent
    -0.73
    sizeCache
    -0.71
     mergeFrom
    -0.68
     onPostExecute
    -0.67
    SequentialGroup
    -0.66
    errHandler
    -0.66
    oredCriteria
    -0.64
    tanleria
    -0.64
    AnchorStyles
    -0.64
    POSITIVE LOGITS
     تانيه
    0.50
    ########.
    0.43
    γά
    0.41
     experiment
    0.40
     experimentation
    0.40
    ma
    0.40
     exercise
    0.40
    بوابة
    0.39
    led
    0.39
    amento
    0.38
    Activations Density 1.594%

    No Known Activations