© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15421
    Prev
    Next
    INDEX
    Explanations

    code

    oai_token-act-pair · gemini-2.0-flash

    code-related content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    Declarations
    -0.55
    LayoutConstraint
    -0.51
    ensitivity
    -0.50
    Билгалдахарш
    -0.48
    ization
    -0.47
    izations
    -0.46
     raft
    -0.45
     Caterina
    -0.45
     Poincaré
    -0.44
    ENZA
    -0.44
    POSITIVE LOGITS
    SourceChecksum
    0.62
    김
    0.56
    문
    0.54
     AssemblyProduct
    0.50
     définiti
    0.50
    횟
    0.50
    공
    0.50
    예
    0.49
    앞
    0.49
    패
    0.47
    Activations Density 32.464%

    No Known Activations