© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 12573
    Prev
    Next
    INDEX
    Explanations

    code snippets using the scikit-learn library in Python

    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_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
    uxxxx
    -0.81
    EDEFAULT
    -0.70
    Portale
    -0.69
     AssemblyTitle
    -0.69
     Quay
    -0.68
    migrationBuilder
    -0.66
    :✨
    -0.66
    ChildScrollView
    -0.66
    RectangleBorder
    -0.64
    تقاوى
    -0.64
    POSITIVE LOGITS
     dedans
    0.59
     vrais
    0.55
     età
    0.53
     vôtre
    0.53
     edad
    0.50
     nôtre
    0.49
    surveys
    0.49
     voisins
    0.49
    binar
    0.47
     virke
    0.47
    Activations Density 12.972%

    No Known Activations