© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 9165
    Prev
    Next
    INDEX
    Explanations

    words related to surveys or research outcomes

    oai_token-act-pair · gemini-2.0-flash

    factors related to healthcare evaluation

    np_token-act-pair-logits · gpt-4o-mini

    Research studies and influences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/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.21.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
     pinulongan
    -0.54
    idelberg
    -0.51
    localctx
    -0.50
    ImGui
    -0.48
    WireFormat
    -0.48
    getSimpleName
    -0.46
     ویکی‌پدیای
    -0.46
    himovic
    -0.46
    upta
    -0.46
     protoimpl
    -0.45
    POSITIVE LOGITS
    出版年
    0.77
     trustworthiness
    0.56
    ########.
    0.54
     attractiveness
    0.53
     affordability
    0.52
     acceptability
    0.52
     perceptions
    0.52
     preparedness
    0.50
     compositional
    0.50
    ponses
    0.50
    Activations Density 4.078%

    No Known Activations