© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3732
    Prev
    Next
    INDEX
    Explanations

    the phrase "of [place]", especially when the place is a legal authority

    oai_token-act-pair · gemini-2.0-flash

    phrases related to legal entities and court documents

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

    of

    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
    mailer
    -0.52
     مواليد
    -0.49
     of
    -0.49
     totul
    -0.45
     locaux
    -0.44
     zake
    -0.44
     fatality
    -0.43
    ipun
    -0.43
    uty
    -0.43
    llan
    -0.43
    POSITIVE LOGITS
     ProtoMessage
    0.83
    UserScript
    0.83
     CreateTagHelper
    0.82
    OGND
    0.70
    MemoryWarning
    0.63
    RTGC
    0.63
    InitVars
    0.61
    PyExc
    0.59
    webElementXpaths
    0.58
    EndGlobalSection
    0.58
    Activations Density 1.019%

    No Known Activations