© 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. 3596
    Prev
    Next
    INDEX
    Explanations

    words related to fields of scientific research

    oai_token-act-pair · gemini-2.0-flash

    research papers

    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
     betweenstory
    -0.70
     ujednoznacz
    -0.65
    BeginContext
    -0.59
    setVerticalGroup
    -0.59
    "]();
    -0.54
    }();
    -0.54
     arras
    -0.51
    انجليز
    -0.51
     referenties
    -0.50
    Liefs
    -0.50
    POSITIVE LOGITS
     linearized
    0.53
    SourceChecksum
    0.50
    AxisAlignment
    0.50
    aternion
    0.49
     zeta
    0.49
    BagConstraints
    0.48
    mura
    0.46
    AutoScale
    0.46
    secta
    0.46
    ctrons
    0.46
    Activations Density 42.109%

    No Known Activations