© 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. 4995
    Prev
    Next
    INDEX
    Explanations

    words related to legal proceedings, writing, and formal documentation

    oai_token-act-pair · gemini-2.0-flash

    hyphens

    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
    verhält
    -0.54
    fören
    -0.51
     Перейти
    -0.51
    freiheit
    -0.51
    ständen
    -0.50
    verlauf
    -0.49
    wapV
    -0.48
    stufen
    -0.48
    ΟΝ
    -0.47
    IntoConstraints
    -0.47
    POSITIVE LOGITS
    -
    2.92
    -<
    1.35
    ‑
    1.32
    -
    1.23
    -$
    1.22
    -​
    1.21
    -...
    1.20
    -*
    1.18
    -\\
    1.16
    -!
    1.16
    Activations Density 21.737%

    No Known Activations