© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9806
    Prev
    Next
    INDEX
    Explanations

    names of academic departments, centers, and institutes

    oai_token-act-pair · gemini-2.0-flash

    Institute

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     initWithFrame
    -0.51
    kirakan
    -0.49
    UserScript
    -0.49
    artifactId
    -0.48
    tagHelperRunner
    -0.48
     bewer
    -0.48
    ślę
    -0.48
    aima
    -0.47
     urbanas
    -0.47
     nahilalakip
    -0.46
    POSITIVE LOGITS
    aritions
    0.59
    बस
    0.57
     المرجع
    0.56
    Referințe
    0.53
    addContainerGap
    0.53
    andaag
    0.52
    urtstag
    0.51
    principalTable
    0.50
     concussion
    0.49
    Референце
    0.49
    Activations Density 0.456%

    No Known Activations