© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4716
    Prev
    Next
    INDEX
    Explanations

    scientific claims and reasoning within research papers.

    oai_token-act-pair · gemini-2.0-flash

    period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     suspect
    -0.54
    enumerate
    -0.53
    脚注の使い方
    -0.53
    constructor
    -0.50
     Rib
    -0.49
    itemize
    -0.49
    ening
    -0.48
     vermute
    -0.48
    qtype
    -0.48
    出版年
    -0.47
    POSITIVE LOGITS
    NamedQueries
    0.55
    expandindo
    0.54
    internalType
    0.53
    Parameteri
    0.53
    aarrggbb
    0.53
    DotNetBar
    0.52
    Viewed
    0.52
    TagHelper
    0.52
    STRENGTH
    0.52
    นี
    0.51
    Activations Density 2.494%

    No Known Activations