© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9274
    Prev
    Next
    INDEX
    Explanations

    short descriptions or summaries

    oai_token-act-pair · gemini-2.0-flash

    summary

    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
    Negative Logits
    verifyException
    -0.50
    monių
    -0.47
     _$
    -0.47
    netic
    -0.47
     Anytime
    -0.46
     NTIS
    -0.45
    useNewUrlParser
    -0.45
     [*]
    -0.45
     zpě
    -0.45
    ometal
    -0.44
    POSITIVE LOGITS
     saites
    0.72
    styleType
    0.67
    Description
    0.66
     description
    0.65
     Description
    0.65
    <bos>
    0.64
    ectoria
    0.64
     ujednoznacz
    0.64
    akterysty
    0.63
    InputBorder
    0.62
    Activations Density 0.808%

    No Known Activations