© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10172
    Prev
    Next
    INDEX
    Explanations

    words related to the preservation of nature

    oai_token-act-pair · gemini-2.0-flash

    conservation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Conservation
    -1.59
     conservation
    -1.55
    Conservation
    -1.52
    conservation
    -1.40
     CONSERVATION
    -1.32
     conserving
    -0.97
     صوتيه
    -0.92
     conservación
    -0.92
     conserve
    -0.90
     conserva
    -0.85
    POSITIVE LOGITS
    <bos>
    0.77
     voran
    0.46
     amely
    0.45
    \]
    0.43
     baru
    0.42
    register
    0.42
     bá
    0.42
     think
    0.41
     De
    0.40
    huriyet
    0.40
    Activations Density 1.434%

    No Known Activations