© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3616
    Prev
    Next
    INDEX
    Explanations

    the word "different" or similar words related to variety

    oai_token-act-pair · gemini-2.0-flash

    different

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -0.87
     way
    -0.60
     very
    -0.60
     most
    -0.50
     whole
    -0.50
     the
    -0.49
     same
    -0.49
     either
    -0.47
     various
    -0.47
     themselves
    -0.47
    POSITIVE LOGITS
     CreateTagHelper
    1.25
    setVerticalGroup
    1.24
     AssemblyProduct
    1.16
    tagHelperRunner
    1.04
     &___
    1.02
    rungsseite
    1.01
    LookAnd
    1.00
    IonicModule
    1.00
     EconPapers
    1.00
    adaptiveStyles
    0.99
    Activations Density 1.067%

    No Known Activations