© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11934
    Prev
    Next
    INDEX
    Explanations

    mentions of specific groups and technologies such as Git, Apache, and Unity.

    oai_token-act-pair · gemini-2.0-flash

    Technical Language

    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
    
    -0.85
    Jeografia
    -0.84
     pinulongan
    -0.78
    ImageContext
    -0.78
    AndEndTag
    -0.77
    StoryboardSegue
    -0.76
    期刊论文
    -0.75
    يميديا
    -0.74
    цездатний
    -0.72
     snippetHide
    -0.71
    POSITIVE LOGITS
     furl
    0.38
    AttributeSet
    0.38
     aliments
    0.37
    jatel
    0.37
    boutin
    0.36
    Data
    0.36
     Mathematik
    0.35
     Needham
    0.35
    Fix
    0.34
    ulisan
    0.34
    Activations Density 0.623%

    No Known Activations