© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9480
    Prev
    Next
    INDEX
    Explanations

    words related to people doing things in specific situations

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     nød
    -0.52
    glises
    -0.52
     iſt
    -0.50
     pouvoit
    -0.49
     étoient
    -0.49
    RegressionTest
    -0.49
    spół
    -0.49
     Motorrad
    -0.49
    ."));
    -0.49
     vocale
    -0.48
    POSITIVE LOGITS
     @"/
    0.74
    ⓧ
    0.60
     propOrder
    0.58
    TagMode
    0.51
    ษัท
    0.50
     mergeFrom
    0.47
    блиоте
    0.47
     snippetHide
    0.45
    ngdoc
    0.45
     dem
    0.44
    Activations Density 0.626%

    No Known Activations