© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12033
    Prev
    Next
    INDEX
    Explanations

    words related to industrial pressing and molding equipment

    oai_token-act-pair · gemini-2.0-flash

    punch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    punch
    -0.54
     punch
    -0.52
    ⓘ
    -0.48
    Punch
    -0.44
    Nin
    -0.44
    ์ตูน
    -0.43
     emp
    -0.43
     Punch
    -0.42
     LCCN
    -0.40
     punches
    -0.40
    POSITIVE LOGITS
    RegressionTest
    0.82
    TestingModule
    0.82
    bootstrapcdn
    0.81
    yntaxException
    0.79
     JAXBElement
    0.68
    ✨:
    0.68
    windowFixed
    0.68
     EconPapers
    0.68
     Normdatei
    0.68
    aarrggbb
    0.68
    Activations Density 9.350%

    No Known Activations