© 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. 10464
    Prev
    Next
    INDEX
    Explanations

    numbers, especially those that indicate dates or numerical references

    oai_token-act-pair · gemini-2.0-flash

    citations and references

    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
     
    -1.27
    ,
    -1.04
    .
    -0.98
    ↵↵
    -0.96
    ↵
    -0.93
     (
    -0.91
    <eos>
    -0.91
    -
    -0.87
    /
    -0.85
     and
    -0.81
    POSITIVE LOGITS
     Efq
    2.36
     myſelf
    2.30
     itſelf
    2.30
    ^(@)
    2.16
     Jefus
    2.16
     Monfieur
    2.03
     Majefty
    2.03
     himſelf
    2.02
     pleaſure
    2.02
     purpoſe
    2.00
    Activations Density 3.025%

    No Known Activations