© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7327
    Prev
    Next
    INDEX
    Explanations

    text where someone is asking for help with a computing problem

    oai_token-act-pair · gemini-2.0-flash

    code/troubleshooting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    tagHelperRunner
    -0.70
     creș
    -0.64
     vrea
    -0.61
     dépos
    -0.60
     ModelExpression
    -0.60
     שוליים
    -0.57
     urm
    -0.56
     culoare
    -0.55
    клопе
    -0.54
     presentazione
    -0.54
    POSITIVE LOGITS
    ыгана
    0.65
    XmlType
    0.62
    featureID
    0.59
    Rhestr
    0.55
    windowFixed
    0.54
    ]")]
    0.54
    __':
    0.53
     ProtoMessage
    0.53
     sint
    0.52
    bcryptjs
    0.52
    Activations Density 1.111%

    No Known Activations