© 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. 2491
    Prev
    Next
    INDEX
    Explanations

    apostrophes and beginning parts of URLs.

    oai_token-act-pair · gemini-2.0-flash

    apostrophe

    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
     برانيه
    -0.57
     bezeichneter
    -0.54
    afficheront
    -0.54
    новниш
    -0.54
     haka
    -0.49
     CGPA
    -0.48
     estimés
    -0.47
    Portale
    -0.47
     BrowserModule
    -0.47
    InsertCommand
    -0.45
    POSITIVE LOGITS
    EndProject
    0.65
    s
    0.65
    A
    0.63
    UpInside
    0.59
    re
    0.57
    makeConstraints
    0.56
    m
    0.56
    F
    0.55
     ExecuteAsync
    0.55
    TagHelper
    0.55
    Activations Density 3.871%

    No Known Activations