© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2746
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to financial applications, paperwork, processes as well as banking.

    oai_token-act-pair · gemini-2.0-flash

    unrecognized or malformed tokens

    np_token-act-pair-logits · gpt-4o-mini

    Financial and employment 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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     aveug
    -0.65
     femininas
    -0.52
     kentang
    -0.52
    webElementXpaths
    -0.52
    stod
    -0.50
    انجليز
    -0.49
     ArrayAdapter
    -0.48
     griega
    -0.48
    ServiceModel
    -0.47
     visuel
    -0.47
    POSITIVE LOGITS
    UnknownFieldSet
    0.70
    :✨
    0.59
    iptables
    0.55
    istoitu
    0.54
    tizens
    0.54
    ']);
    0.53
    🏻‍♀️
    0.52
    ']))
    0.51
    NameInMap
    0.50
     HttpNotFound
    0.50
    Activations Density 0.422%

    No Known Activations