© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2596
    Prev
    Next
    INDEX
    Explanations

    the letter "N" at the beginning of words, especially in contexts related to names, organizations, or product codes.

    oai_token-act-pair · gemini-2.0-flash

    N

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    ScopeManager
    -0.78
    NgModule
    -0.68
    fromnode
    -0.64
    bootstrapcdn
    -0.63
    RectangleBorder
    -0.62
    StructEnd
    -0.61
    TagHelper
    -0.60
    Jîn
    -0.59
    WillAppear
    -0.58
    AnchorStyles
    -0.56
    POSITIVE LOGITS
    icoot
    0.51
    الدراسه
    0.48
    rable
    0.46
     normalement
    0.45
    izr
    0.45
    iston
    0.45
    unten
    0.44
    ОД
    0.44
    ochet
    0.44
    uts
    0.44
    Activations Density 1.952%

    No Known Activations