© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1460
    Prev
    Next
    INDEX
    Explanations

    technical writing that includes quantities, measurements, and currency

    oai_token-act-pair · gemini-2.0-flash

    be

    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
     disambiguazione
    -0.61
     kaarangay
    -0.60
    tros
    -0.58
    ArgsConstructor
    -0.58
    lierung
    -0.55
    llte
    -0.51
    WriteTagHelper
    -0.49
    ┻
    -0.49
     Suppression
    -0.48
    tanleria
    -0.48
    POSITIVE LOGITS
    UnsafeEnabled
    0.55
    memoized
    0.54
    ContentAsync
    0.53
     חיצוניים
    0.48
    LabelTagHelper
    0.48
    Diwedd
    0.48
    ectady
    0.47
    UnknownFields
    0.46
     <<<<<<<<<<<<<<
    0.45
     te
    0.45
    Activations Density 2.204%

    No Known Activations