© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16287
    Prev
    Next
    INDEX
    Explanations

    phrases containing "the thought of" or "the sight of" as well as references to contemplation, opinion, and ideas.

    oai_token-act-pair · gemini-2.0-flash

    thoughts and contemplation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     صوتيه
    -0.98
    GraphicsUnit
    -0.94
    awtextra
    -0.79
    /**
    -0.77
    AddTagHelper
    -0.73
    ">—
    -0.73
    posedge
    -0.71
     nahilalakip
    -0.70
    mybatisplus
    -0.69
    CppCodeGen
    -0.69
    POSITIVE LOGITS
     test
    0.50
    iana
    0.48
     arra
    0.45
    estion
    0.45
    sna
    0.44
    alt
    0.44
    gni
    0.43
     tested
    0.42
     teor
    0.41
    set
    0.41
    Activations Density 1.458%

    No Known Activations