© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6802
    Prev
    Next
    INDEX
    Explanations

    PHP code that prints/displays output to the user

    oai_token-act-pair · gemini-2.0-flash

    echo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     echo
    -1.44
    echo
    -1.09
     echoes
    -0.99
     Echo
    -0.92
    Echo
    -0.91
     echoing
    -0.76
     ECHO
    -0.68
     echoed
    -0.66
     Echoes
    -0.60
    ysty
    -0.57
    POSITIVE LOGITS
     OnInit
    0.86
    rungsseite
    0.85
     BoxDecoration
    0.73
    BagLayout
    0.67
    Referencie
    0.66
    AddHtmlAttribute
    0.63
    BoxLayout
    0.62
     FontWeight
    0.59
    rxjs
    0.58
    Спољашње
    0.57
    Activations Density 0.165%

    No Known Activations