© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2034
    Prev
    Next
    INDEX
    Explanations

    code snippets and UI related keywords like button and press

    oai_token-act-pair · gemini-2.0-flash

    ok close

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     &___
    -0.88
    })*/
    -0.81
     kasarigan
    -0.77
     Efq
    -0.77
    });*/
    -0.74
    AxisAlignment
    -0.74
    évaluateur
    -0.71
    MessageTagHelper
    -0.69
     Савезне
    -0.68
    BibitemShut
    -0.68
    POSITIVE LOGITS
     OK
    0.84
    OK
    0.81
     close
    0.77
     ok
    0.75
    ok
    0.75
     Close
    0.73
     Ok
    0.72
    Close
    0.69
    close
    0.66
    Ok
    0.66
    Activations Density 1.380%

    No Known Activations