© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2558
    Prev
    Next
    INDEX
    Explanations

    words related to manufactured processes and formulas

    oai_token-act-pair · gemini-2.0-flash

    steps in a procedure

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    帖最后由
    -0.52
    SuspendLayout
    -0.46
    仑
    -0.40
    клопе
    -0.39
    onomics
    -0.38
    GAIN
    -0.37
    ッジ
    -0.36
    urlencoded
    -0.36
     Cavendish
    -0.36
    sendFile
    -0.36
    POSITIVE LOGITS
     step
    2.95
     steps
    2.75
    step
    2.69
     Step
    2.58
    Step
    2.53
     Steps
    2.41
    steps
    2.33
     STEP
    2.20
    STEP
    2.19
    Steps
    2.14
    Activations Density 4.838%

    No Known Activations