© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14077
    Prev
    Next
    INDEX
    Explanations

    words located near concepts of comparison, proximity, or change

    oai_token-act-pair · gemini-2.0-flash

    close

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     close
    -1.37
    close
    -1.09
     Close
    -1.08
    Close
    -1.00
     CLOSE
    -0.96
     closer
    -0.93
     near
    -0.91
     closest
    -0.89
     closeness
    -0.87
     proche
    -0.84
    POSITIVE LOGITS
    PRWEB
    0.73
     propOrder
    0.68
     Numerade
    0.67
     ujednoznacz
    0.67
    FontOfSize
    0.67
     AppModule
    0.65
     ModelExpression
    0.64
     AssemblyCulture
    0.64
     ">=
    0.63
    medriver
    0.63
    Activations Density 37.756%

    No Known Activations