© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2360
    Prev
    Next
    INDEX
    Explanations

    language indicative of new and innovative effort such as "first," "pioneering," and "groundbreaking."

    oai_token-act-pair · gemini-2.0-flash

    innovation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    AsUp
    -0.81
     >=",
    -0.77
    WireFormat
    -0.75
     препратки
    -0.74
    __':
    -0.74
    UIControlState
    -0.70
    tableFuture
    -0.69
    makeText
    -0.69
    InstrumentedTest
    -0.67
    kháu
    -0.67
    POSITIVE LOGITS
    XXXXX
    0.48
     function
    0.46
     XX
    0.39
    دانشنامهٔ
    0.37
     thickly
    0.37
    ++]
    0.36
    ++];
    0.36
    Function
    0.36
    ينه
    0.36
    ciach
    0.36
    Activations Density 2.250%

    No Known Activations