© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12667
    Prev
    Next
    INDEX
    Explanations

    text that contains letters Q and A, or questions beginning with "or"

    oai_token-act-pair · gemini-2.0-flash

    Questions/Options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    addContainerGap
    -0.76
    XmlAccessorType
    -0.71
    WebServlet
    -0.66
     getItemId
    -0.65
    ghouse
    -0.63
    ]='\
    -0.63
     FetchType
    -0.62
    eload
    -0.60
     Efq
    -0.59
    LayoutStyle
    -0.58
    POSITIVE LOGITS
    ?
    0.88
    )?
    0.73
    ？
    0.61
    ؟
    0.59
     ?
    0.59
    ?:
    0.57
    %?
    0.56
    ？　
    0.53
    ?)
    0.52
    ?(
    0.52
    Activations Density 1.129%

    No Known Activations