© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2316
    Prev
    Next
    INDEX
    Explanations

    scientific text about testing procedures

    oai_token-act-pair · gemini-2.0-flash

    ochrom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    apimachinery
    -0.49
     regularity
    -0.49
     hurry
    -0.49
    )'
    -0.47
    utters
    -0.46
    }$,
    -0.46
    oda
    -0.45
    msubsup
    -0.44
     postulates
    -0.44
    Aktualisiert
    -0.44
    POSITIVE LOGITS
    NOPQRST
    0.70
     utafitiHapana
    0.65
     doInBackground
    0.59
    centralwidget
    0.57
    IndentedString
    0.57
     kasarigan
    0.56
    PhysRevLett
    0.56
    findpost
    0.55
    waitKey
    0.54
     resourceCulture
    0.54
    Activations Density 3.259%

    No Known Activations