© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6706
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to environmental issues and extraction of resources

    oai_token-act-pair · gemini-2.0-flash

    mine

    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
     Wolken
    -0.57
     Wikimedijinoj
    -0.56
     PVA
    -0.49
    EndGlobalSection
    -0.48
    Drying
    -0.48
    rhosis
    -0.48
    ciphertext
    -0.47
    annelse
    -0.47
    SCS
    -0.46
     Cereal
    -0.45
    POSITIVE LOGITS
     mine
    1.78
    mine
    1.46
     Mine
    1.45
    Mine
    1.44
     mines
    1.41
     MINE
    1.36
    mines
    1.29
    MINE
    1.25
     Mines
    1.13
     mined
    1.12
    Activations Density 3.917%

    No Known Activations