© 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. 603
    Prev
    Next
    INDEX
    Explanations

    the word "further" and words immediately adjacent to it

    oai_token-act-pair · gemini-2.0-flash

    further

    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
     further
    -2.42
    further
    -2.13
    Further
    -2.11
     Further
    -2.05
     FURTHER
    -1.80
    FURTHER
    -1.48
     farther
    -1.45
    进一步
    -1.22
    urther
    -1.21
     дальней
    -1.04
    POSITIVE LOGITS
     AssemblyCulture
    0.78
    interopRequire
    0.75
     EconPapers
    0.72
     personalizada
    0.68
    ReusableCell
    0.65
    httphttps
    0.63
    TagMode
    0.63
     MainAxisSize
    0.62
    UnitTesting
    0.61
    NewLabel
    0.60
    Activations Density 2.126%

    No Known Activations