© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 900
    Prev
    Next
    INDEX
    Explanations

    lines of PHP code along with surrounding documentation

    oai_token-act-pair · gemini-2.0-flash

    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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     front
    -0.46
    ServiceModel
    -0.45
    Front
    -0.44
    MARK
    -0.43
    done
    -0.42
     néglig
    -0.42
    WillAppear
    -0.41
    cupa
    -0.41
     βα
    -0.41
    kool
    -0.41
    POSITIVE LOGITS
     noDo
    0.77
    তথ্যসূত্র
    0.71
     perfons
    0.70
    IsPostBack
    0.69
    viewDidLoad
    0.69
    ſelf
    0.69
    发表于
    0.69
     kasarigan
    0.68
    verwijspagina
    0.68
     مشين
    0.67
    Activations Density 0.709%

    No Known Activations