© 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. 11644
    Prev
    Next
    INDEX
    Explanations

    article titles or article summaries

    oai_token-act-pair · gemini-2.0-flash

    Read More story

    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
    Autoritní
    -0.93
     autorytatywna
    -0.92
    AndEndTag
    -0.87
     fieldNum
    -0.80
    :✨
    -0.80
     Normdatei
    -0.79
     ostavi
    -0.77
    MessageOf
    -0.76
     ProtoMessage
    -0.71
    Jeografia
    -0.70
    POSITIVE LOGITS
     Sarm
    0.47
     dayan
    0.45
     reactant
    0.40
    l
    0.39
    MigrationBuilder
    0.38
    嶺
    0.38
     Decke
    0.37
    setMessage
    0.37
     αλ
    0.37
     drawn
    0.36
    Activations Density 0.720%

    No Known Activations