© 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. 11255
    Prev
    Next
    INDEX
    Explanations

    the word 'the' preceded by a word with a short length

    oai_token-act-pair · gemini-2.0-flash

    articles "a" and "the"

    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
    parsedMessage
    -0.50
    spender
    -0.47
     oprot
    -0.47
    ❞
    -0.46
    fhir
    -0.46
     continúas
    -0.46
     =",
    -0.45
    })}\
    -0.45
     himo
    -0.44
    )";
    -0.44
    POSITIVE LOGITS
     whole
    3.67
    whole
    3.48
    Whole
    3.05
     WHOLE
    2.83
     Whole
    2.78
     entire
    2.25
     ganzen
    2.09
     ganze
    2.09
     Entire
    1.85
    entire
    1.75
    Activations Density 2.824%

    No Known Activations