© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 16040
    Prev
    Next
    INDEX
    Explanations

    mentions of trees

    oai_token-act-pair · gemini-2.0-flash

    trees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     —
    -0.57
    odied
    -0.56
    gemaakt
    -0.55
    CJK
    -0.54
    vode
    -0.54
    ppure
    -0.52
     nearly
    -0.51
    m
    -0.51
    min
    -0.51
     to
    -0.50
    POSITIVE LOGITS
     Monfieur
    1.11
     themſelves
    1.09
     ſeveral
    1.09
    Personendaten
    1.05
     pleaſure
    1.04
     Majefty
    1.02
     Shakspeare
    1.00
     itſelf
    1.00
     myſelf
    0.99
     Conſ
    0.98
    Activations Density 0.660%

    No Known Activations