© 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. 4158
    Prev
    Next
    INDEX
    Explanations

    code snippets and related terms like "value", "function", "string", and "BOOST_CHECK"

    oai_token-act-pair · gemini-2.0-flash

    f

    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
     supérieures
    -0.58
     démocr
    -0.56
     polvere
    -0.56
     engraçadas
    -0.55
     varandra
    -0.54
     élevées
    -0.54
     religieuses
    -0.53
     pubblici
    -0.53
     présentés
    -0.52
     réguli
    -0.52
    POSITIVE LOGITS
    gn
    0.75
     snippetHide
    0.69
    ds
    0.69
    ts
    0.69
    dy
    0.67
    nt
    0.67
    dd
    0.65
    ld
    0.65
    td
    0.65
    ks
    0.65
    Activations Density 18.589%

    No Known Activations