© 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. 8954
    Prev
    Next
    INDEX
    Explanations

    context related to composers

    oai_token-act-pair · gemini-2.0-flash

    Text/article context

    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
    }{*}{
    -0.54
     licences
    -0.53
     licenses
    -0.52
     licence
    -0.50
     poda
    -0.48
    __':
    -0.48
     conosco
    -0.48
    ัง
    -0.47
     चुनें
    -0.46
     randomised
    -0.46
    POSITIVE LOGITS
     utafitiHapana
    0.69
     bezeichneter
    0.67
    ArrowToggle
    0.63
    quelize
    0.62
    lwjgl
    0.56
    iaceae
    0.56
    TypedDataSet
    0.55
    hoeddwyd
    0.55
    Hauptartikel
    0.55
    giphy
    0.53
    Activations Density 3.212%

    No Known Activations