© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 12273
    Prev
    Next
    INDEX
    Explanations

    common words used to link and explain ideas.

    oai_token-act-pair · gemini-2.0-flash

    Java code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     other
    -2.72
    other
    -2.47
     Other
    -2.33
    Other
    -2.28
     autres
    -2.19
     OTHER
    -2.17
    OTHER
    -2.03
     otras
    -1.95
     otros
    -1.91
     outras
    -1.91
    POSITIVE LOGITS
     ano
    0.61
    ```
    0.43
    Ano
    0.43
    writeField
    0.42
    ano
    0.40
    \]
    0.38
     any
    0.38
    oa̍t
    0.38
    detectChanges
    0.38
     anot
    0.37
    Activations Density 5.312%

    No Known Activations