© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9856
    Prev
    Next
    INDEX
    Explanations

    parts related to engines and cars

    oai_token-act-pair · gemini-2.0-flash

    car and boat parts

    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
    astify
    -0.68
    Havolalar
    -0.55
    ReusableCell
    -0.49
    erdan
    -0.48
    ferrer
    -0.48
     saites
    -0.47
     protoimpl
    -0.47
     excru
    -0.47
    DotNetBar
    -0.46
     “
    -0.45
    POSITIVE LOGITS
     themſelves
    0.75
     Monfieur
    0.74
     auffi
    0.71
     raiſ
    0.69
     itſelf
    0.69
     ſever
    0.69
     leſs
    0.68
     himſelf
    0.66
     myſelf
    0.66
     ſtate
    0.64
    Activations Density 1.518%

    No Known Activations