© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2783
    Prev
    Next
    INDEX
    Explanations

    the stems "group", "po", "id", "p", and "gr"

    oai_token-act-pair · gemini-2.0-flash

    Code/technical "group" references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     lenge
    -0.54
    avax
    -0.49
     interpolation
    -0.48
     Sinon
    -0.48
    脚注の使い方
    -0.48
     taxes
    -0.48
     Fenn
    -0.46
     interpolate
    -0.44
    ลา
    -0.44
     تن
    -0.43
    POSITIVE LOGITS
     kasarigan
    0.84
     getGroup
    0.78
     Grou
    0.78
     Groups
    0.77
     grp
    0.73
     Grouping
    0.73
     FormGroup
    0.73
    Groups
    0.71
    DispatchToProps
    0.71
     groups
    0.69
    Activations Density 2.600%

    No Known Activations