© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13168
    Prev
    Next
    INDEX
    Explanations

    words that are commonly used in legal and technical documents.

    oai_token-act-pair · gemini-2.0-flash

    doing or creating something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    GraphicsUnit
    -0.75
    :+:
    -0.67
    UserScript
    -0.64
    saraba
    -0.62
     "..\..\..\
    -0.60
     säll
    -0.60
     thereafter
    -0.59
     xlink
    -0.59
    Datuak
    -0.57
     Afterwards
    -0.57
    POSITIVE LOGITS
     بيها
    0.51
    tidaknya
    0.46
     ro
    0.45
    Gren
    0.45
    äsche
    0.45
    yordu
    0.44
    hlander
    0.44
    밖
    0.44
    زال
    0.43
    jercicios
    0.43
    Activations Density 3.259%

    No Known Activations