© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4831
    Prev
    Next
    INDEX
    Explanations

    words and partial words related to project completion and time

    oai_token-act-pair · gemini-2.0-flash

    completion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     completed
    -0.88
     finished
    -0.86
     completion
    -0.85
     finish
    -0.81
    finish
    -0.79
    completed
    -0.79
     finishing
    -0.79
    finished
    -0.78
     Finished
    -0.75
    Completed
    -0.72
    POSITIVE LOGITS
    AutoScaleMode
    0.84
    ագրություններ
    0.75
    AccessorTable
    0.69
    zzleHttp
    0.69
    bootstrapcdn
    0.69
    脚注の使い方
    0.69
     AssemblyProduct
    0.67
    ьаж
    0.66
     الحره
    0.66
    OGND
    0.65
    Activations Density 27.545%

    No Known Activations