© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14555
    Prev
    Next
    INDEX
    Explanations

    language related to land conservation strategy

    oai_token-act-pair · gemini-2.0-flash

    development

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    inger
    -0.51
    labelledby
    -0.49
     educativos
    -0.46
    ningens
    -0.46
     éduc
    -0.46
    verket
    -0.46
    éducation
    -0.46
     épic
    -0.45
    unea
    -0.45
     alimentazione
    -0.45
    POSITIVE LOGITS
     development
    1.19
    Development
    1.07
     DEVELOPMENT
    1.06
     Development
    1.06
    development
    1.02
    Developing
    0.96
    DEVELOPMENT
    0.93
     DEVELOP
    0.91
     developing
    0.90
     Developing
    0.90
    Activations Density 1.580%

    No Known Activations