© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8232
    Prev
    Next
    INDEX
    Explanations

    code snippets or numerical identifiers

    oai_token-act-pair · gemini-2.0-flash

    Code/technical document snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    .
    -0.29
    <eos>
    -0.15
    in
    -0.13
    …
    -0.13
    4
    -0.12
    3
    -0.12
    –
    -0.12
    ,
    -0.11
    us
    -0.11
    2
    -0.10
    POSITIVE LOGITS
     Efq
    2.05
     myſelf
    1.93
     Monfieur
    1.91
    ſelf
    1.85
     Jefus
    1.84
     itſelf
    1.83
     Majefty
    1.80
     Theſe
    1.78
     pleaſure
    1.74
     houſe
    1.73
    Activations Density 36.161%

    No Known Activations