© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2643
    Prev
    Next
    INDEX
    Explanations

    words related to technical specifications and mechanical components, particularly those involving springs and couplings

    oai_token-act-pair · gemini-2.0-flash

    spring

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    spring
    -1.27
     spring
    -1.26
    Spring
    -1.20
     springs
    -1.19
     Spring
    -1.17
    springs
    -1.15
    SPRING
    -1.00
     SPRING
    -0.98
     Springs
    -0.97
     SPRINGS
    -0.91
    POSITIVE LOGITS
    AddHtmlAttribute
    0.66
    ConverterFactory
    0.64
    ])).
    0.61
    }))
    0.60
    bulin
    0.53
     snippetHide
    0.53
    HasAnnotation
    0.52
    CodeAttribute
    0.52
     препратки
    0.52
     SLIP
    0.50
    Activations Density 13.392%

    No Known Activations