© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8739
    Prev
    Next
    INDEX
    Explanations

    a grab bag of positive sentiment and movie/entertainment buzz words

    oai_token-act-pair · gemini-2.0-flash

    Quotes and commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    QRect
    -0.56
    +#+
    -0.52
    viewDidLoad
    -0.49
    lète
    -0.48
    Subsystem
    -0.46
    tabular
    -0.46
    WithIdentifier
    -0.45
    ностях
    -0.45
    olid
    -0.44
     MonoBehaviour
    -0.44
    POSITIVE LOGITS
    contentLoaded
    0.71
    Билгалдахарш
    0.69
    يكب
    0.68
    ValueStyle
    0.62
    Referencie
    0.62
    LEncoder
    0.60
     GenerationType
    0.59
    JsonHelper
    0.59
     /\.(
    0.59
     Biôgrafia
    0.56
    Activations Density 3.721%

    No Known Activations