© 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. 10053
    Prev
    Next
    INDEX
    Explanations

    fragments of words in what appears to be Croatian

    oai_token-act-pair · gemini-2.0-flash

    french adjectives

    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
    RegressionTest
    -0.88
     initWithFrame
    -0.73
    SequentialGroup
    -0.72
     itſelf
    -0.65
     GenerationType
    -0.63
    WebServlet
    -0.62
    matchCondition
    -0.62
    AutoScale
    -0.60
     ACCOM
    -0.60
    rizona
    -0.59
    POSITIVE LOGITS
     européennes
    0.60
     vectorielles
    0.54
     élevées
    0.51
     actuelles
    0.49
     behövs
    0.47
     rurales
    0.46
     alimentaires
    0.46
     actuels
    0.46
     précédentes
    0.45
     apporté
    0.44
    Activations Density 0.117%

    No Known Activations