© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1655
    Prev
    Next
    INDEX
    Explanations

    code snippets

    oai_token-act-pair · gemini-2.0-flash

    Code related

    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
    igu
    -0.27
    ̀n
    -0.26
    ­
    -0.25
    odo
    -0.25
    bigcirc
    -0.25
    的话
    -0.25
    displaystyle
    -0.25
    asco
    -0.24
    avimo
    -0.24
    atr
    -0.24
    POSITIVE LOGITS
     ainfi
    0.65
     feroit
    0.57
     auroit
    0.54
     plufieurs
    0.54
    WORKING
    0.52
    ALBUM
    0.52
     enfans
    0.52
     étoit
    0.52
    SERVICE
    0.51
    PAYMENT
    0.51
    Activations Density 16.501%

    No Known Activations