© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 11139
    Prev
    Next
    INDEX
    Explanations

    letters that appear in the middle of seemingly random strings of characters

    oai_token-act-pair · gemini-2.0-flash

    non-english text/code

    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
    id
    -0.82
    ic
    -0.79
    AS
    -0.79
    on
    -0.77
    is
    -0.77
    AT
    -0.76
    AC
    -0.74
    al
    -0.72
    it
    -0.70
    om
    -0.68
    POSITIVE LOGITS
     ویکی‌پدی
    0.80
     سكانية
    0.78
    دانشنامهٔ
    0.78
    WebVitals
    0.69
     autorytatywna
    0.68
    titleMargin
    0.66
    OGND
    0.65
    StoryboardSegue
    0.65
    tagHelperRunner
    0.63
     cherchés
    0.63
    Activations Density 4.239%

    No Known Activations