© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11778
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to technical issues in machines, especially when troubleshooting

    oai_token-act-pair · gemini-2.0-flash

    Computer hardware/software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    MigrationBuilder
    -0.59
     saites
    -0.58
     Waray
    -0.56
     Jefus
    -0.54
    }))
    -0.53
     doInBackground
    -0.52
     Shakspeare
    -0.52
    Παραπομπές
    -0.52
    spac
    -0.52
     Theſe
    -0.51
    POSITIVE LOGITS
     circuitry
    0.68
     motherboard
    0.63
     software
    0.63
     Processor
    0.62
    sistors
    0.61
     EconPapers
    0.60
     transistors
    0.60
     processor
    0.60
     antenna
    0.59
     Software
    0.59
    Activations Density 3.987%

    No Known Activations