© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11760
    Prev
    Next
    INDEX
    Explanations

    technical words related to electronic circuits, signals, and timing.

    oai_token-act-pair · gemini-2.0-flash

    Technical specifications/devices

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     Efq
    -2.13
     myſelf
    -1.92
     Jefus
    -1.91
     Monfieur
    -1.91
    ^(@)
    -1.84
     Majefty
    -1.82
     ―――――
    -1.75
     Theſe
    -1.73
     itſelf
    -1.73
     $_"
    -1.70
    POSITIVE LOGITS
    <eos>
    0.75
    ↵↵
    0.59
    ↵
    0.52
     
    0.49
    ...
    0.48
    -
    0.47
    .
    0.45
    </strong>
    0.44
      
    0.43
    /
    0.42
    Activations Density 24.006%

    No Known Activations