© 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. 9508
    Prev
    Next
    INDEX
    Explanations

    words that are part of a non-English language, possibly Croatian or Serbian

    oai_token-act-pair · gemini-2.0-flash

    words related to verification and registration processes

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

    Facebook account kit/foreign languages

    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
    AnchorStyles
    -0.77
    awtextra
    -0.70
    HtmlAttribute
    -0.70
    PyExc
    -0.66
    TagMode
    -0.64
    successfully
    -0.59
    HostException
    -0.59
     ModelExpression
    -0.58
     <>",
    -0.57
    IUrlHelper
    -0.57
    POSITIVE LOGITS
    licative
    0.65
    atalos
    0.60
    ographical
    0.58
    YTICAL
    0.57
    Sortable
    0.55
    lographic
    0.52
     Danish
    0.52
     című
    0.51
    lytic
    0.51
    umatic
    0.51
    Activations Density 0.220%

    No Known Activations