© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11287
    Prev
    Next
    INDEX
    Explanations

    words that are cut off mid-word and continued on a new line and possible misspellings due to character encoding

    oai_token-act-pair · gemini-2.0-flash

    Code/Chat logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Turch
    -0.50
     Paglinawan
    -0.49
    introduce
    -0.49
     intracellular
    -0.48
    rawDesc
    -0.46
    ObjectContext
    -0.46
     FORMATION
    -0.46
    排
    -0.46
     Introduce
    -0.45
     bild
    -0.45
    POSITIVE LOGITS
    >`;
    0.82
    })$}
    0.78
    +#+
    0.70
     }</
    0.69
     <>",
    0.69
    BufferException
    0.69
     }}$}
    0.69
    )':
    0.68
    ]";
    0.67
     ostavi
    0.66
    Activations Density 0.346%

    No Known Activations