© 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. 25-GEMMASCOPE-TRANSCODER-16K
    4. 13322
    Prev
    Next
    INDEX
    Explanations

    words associated with circuit design and other highly technical fields

    oai_token-act-pair · gemini-2.0-flash

    technical/scientific text

    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
    ghijklmnop
    -0.88
    ftant
    -0.84
     Majefty
    -0.84
     iſt
    -0.81
    adeloupe
    -0.79
    iffance
    -0.79
     houſe
    -0.79
     pleaſure
    -0.78
    iffion
    -0.78
    ollary
    -0.77
    POSITIVE LOGITS
    R
    0.78
    et
    0.78
    L
    0.75
    a
    0.74
    S
    0.72
    as
    0.72
    ap
    0.71
    G
    0.68
    C
    0.68
    h
    0.68
    Activations Density 44.216%

    No Known Activations