© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11778
    Prev
    Next
    INDEX
    Explanations

    uses of numbers relating to amounts, distances, velocities or equations

    oai_token-act-pair · gemini-2.0-flash

    terms related to independence or existence

    np_token-act-pair-logits · gpt-4o-mini

    physics and measurements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    homonymie
    -1.02
    ########.
    -0.92
    AddTagHelper
    -0.91
    SharedDtor
    -0.90
    expandindo
    -0.85
     CreateTagHelper
    -0.81
    featureID
    -0.80
     doubtnut
    -0.79
    StructEnd
    -0.79
    CloseOperation
    -0.77
    POSITIVE LOGITS
     her
    0.46
     the
    0.46
     indépendant
    0.42
    镜
    0.42
    ..
    0.41
     me
    0.41
    ...
    0.40
     O
    0.40
    ื่อน
    0.40
     naturelle
    0.39
    Activations Density 9.613%

    No Known Activations