© 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. 7950
    Prev
    Next
    INDEX
    Explanations

    mixed Spanish language and technical references with links to Panama

    oai_token-act-pair · gemini-2.0-flash

    code and numbering

    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
    LookAnd
    -0.74
    URLException
    -0.46
     vectorielles
    -0.42
     consciência
    -0.42
    řízení
    -0.42
    chinese
    -0.41
     nobis
    -0.41
    GEBURTSDATUM
    -0.41
     déploy
    -0.41
    japanese
    -0.40
    POSITIVE LOGITS
    ™.
    0.61
    ConstraintMaker
    0.58
     kasarigan
    0.56
    EntityFramework
    0.56
     '*')
    0.55
    úa
    0.55
     mil
    0.55
    ™,
    0.54
    tagHelperRunner
    0.54
    <>();
    0.54
    Activations Density 12.439%

    No Known Activations