© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10673
    Prev
    Next
    INDEX
    Explanations

    words related to computer code, math or logic

    oai_token-act-pair · gemini-2.0-flash

    Code and math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     مشين
    -0.93
    ghijkl
    -0.72
    glGen
    -0.71
    󠁣
    -0.70
    󠁧
    -0.69
    verhältnisse
    -0.66
    GHIJKLM
    -0.66
    reciation
    -0.66
    componentDid
    -0.65
    glBind
    -0.64
    POSITIVE LOGITS
    <bos>
    0.88
    ⓧ
    0.71
    InjectAttribute
    0.68
    '
    0.61
     Normdatei
    0.60
    Datuak
    0.59
    ’
    0.59
    ​
    0.54
    ArrowToggle
    0.50
    elemField
    0.49
    Activations Density 4.407%

    No Known Activations