© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 15579
    Prev
    Next
    INDEX
    Explanations

    a specific encryption code within a javascript tag

    oai_token-act-pair · gemini-2.0-flash

    Detects code and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    KommentareTeilen
    -0.67
    帖最后由
    -0.54
     di
    -0.53
     I
    -0.52
     van
    -0.51
     ,
    -0.51
     y
    -0.50
    ERVE
    -0.49
     ten
    -0.49
     (
    -0.49
    POSITIVE LOGITS
     doubtnut
    0.99
     ―――――
    0.85
     itſelf
    0.85
     myſelf
    0.82
     ་་
    0.82
     Anſ
    0.79
     uniqlo
    0.78
     StringTokenizer
    0.78
     dreamstime
    0.74
     Reſ
    0.74
    Activations Density 0.165%

    No Known Activations