© 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. 10222
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to computational analysis, automation, and systems.

    oai_token-act-pair · gemini-2.0-flash

    automation

    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
     automated
    -0.90
     automatically
    -0.90
     Automatically
    -0.88
     Automated
    -0.88
     Auto
    -0.88
     automat
    -0.84
     automatic
    -0.84
    automated
    -0.84
     automation
    -0.84
     auto
    -0.81
    POSITIVE LOGITS
     виправивши
    0.55
     nogen
    0.47
    \{(
    0.47
     accompagné
    0.47
     Eust
    0.47
    Brainz
    0.47
     conferencia
    0.46
     instalada
    0.46
    }`)
    0.46
     sanitaires
    0.46
    Activations Density 12.948%

    No Known Activations