© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 13103
    Prev
    Next
    INDEX
    Explanations

    words and phrases frequently used in academic, legal, and technical writing.

    oai_token-act-pair · gemini-2.0-flash

    further

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     estekak
    -0.76
    bootstrapcdn
    -0.71
    RegressionTest
    -0.70
    complexContent
    -0.67
    KEYCODE
    -0.66
    Chham
    -0.65
    principalTable
    -0.65
    XmlAccessType
    -0.65
     متعلقه
    -0.64
    ngdoc
    -0.63
    POSITIVE LOGITS
     further
    3.47
    further
    3.22
    Further
    3.11
     Further
    3.09
     FURTHER
    2.80
    FURTHER
    2.38
    进一步
    1.91
     farther
    1.89
     weiter
    1.70
     verder
    1.67
    Activations Density 7.484%

    No Known Activations