© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12832
    Prev
    Next
    INDEX
    Explanations

    text mentioning groups operating in the region of Bangladesh, India and Myanmar, specially between 1970 and 2000

    oai_token-act-pair · gemini-2.0-flash

    specific identifiers or terms related to official entities

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

    Geographical/Geopolitical references

    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
    elemField
    -0.75
     ExecuteAsync
    -0.74
    #+#
    -0.73
     AssemblyVersion
    -0.71
    TagHelper
    -0.68
     snippetHide
    -0.68
     FetchType
    -0.67
    principalColumn
    -0.65
    InitVars
    -0.63
    InputTagHelper
    -0.62
    POSITIVE LOGITS
     correctes
    0.51
    ()))
    0.46
    pro
    0.45
    Pro
    0.43
     real
    0.42
    XmlAccessType
    0.42
     S
    0.42
    LLocation
    0.42
    ,
    0.41
    Event
    0.41
    Activations Density 0.927%

    No Known Activations