© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10786
    Prev
    Next
    INDEX
    Explanations

    references to the word "tree"

    oai_token-act-pair · gemini-2.0-flash

    tree

    np_max-act-logits · gemini-2.0-flash

    terms related to trees

    np_token-act-pair-logits · gpt-4o-mini
    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
     plants
    -1.62
     plant
    -1.54
     Plants
    -1.38
     Plant
    -1.38
    Plant
    -1.35
    Plants
    -1.32
    plants
    -1.30
    plant
    -1.30
     leaf
    -1.30
     PLANT
    -1.28
    POSITIVE LOGITS
     FontWeight
    0.55
    PasswordEncoder
    0.52
    Rigidbody
    0.47
    oneta
    0.45
     TextInputType
    0.43
     تضيفلها
    0.43
    inWeight
    0.42
    DataSetChanged
    0.42
    coda
    0.42
     Rigidbody
    0.41
    Activations Density 0.517%

    No Known Activations