© 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. 8669
    Prev
    Next
    INDEX
    Explanations

    Japanese verbs expressing desire or possibility

    oai_token-act-pair · gemini-2.0-flash

    words related to code execution and error handling

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

    Initiating output

    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
    LayoutInflater
    -0.55
    UpInside
    -0.54
    tų
    -0.52
    dze
    -0.51
    RefreshLayout
    -0.50
     onCreateView
    -0.48
    requireNonNull
    -0.47
     tuyến
    -0.47
    arkov
    -0.46
     siêu
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.70
    Kjelder
    0.68
    ValueStyle
    0.66
     didac
    0.60
    IsContent
    0.59
     Infórmanos
    0.58
    SharedDtor
    0.58
    GraphicsUnit
    0.58
     Wikimedijinoj
    0.57
     AspNetCore
    0.57
    Activations Density 0.227%

    No Known Activations