© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2510
    Prev
    Next
    INDEX
    Explanations

    Code snippets and special characters

    oai_token-act-pair · gemini-2.0-flash

    machine learning concepts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    RectangleBorder
    -1.02
     disambiguazione
    -0.94
    
    -0.90
    MigrationBuilder
    -0.86
    matchCondition
    -0.86
    writeField
    -0.86
    styleType
    -0.84
     للاسماء
    -0.82
    AnchorStyles
    -0.82
    bootstrapcdn
    -0.82
    POSITIVE LOGITS
    inference
    0.59
     perhatian
    0.56
    LSTM
    0.54
    epochs
    0.53
    predictions
    0.53
    gradients
    0.52
    tensors
    0.52
    predictor
    0.52
    embeddings
    0.51
    ratios
    0.50
    Activations Density 12.840%

    No Known Activations