© 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. 12140
    Prev
    Next
    INDEX
    Explanations

    percentages, sometimes numbers with "autos" in them

    oai_token-act-pair · gemini-2.0-flash

    cent

    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
     cent
    -2.34
    cent
    -1.70
    Cent
    -1.64
     Cent
    -1.63
     CENT
    -1.37
    CENT
    -1.32
     cents
    -1.19
     centri
    -1.09
     centroid
    -1.05
     Cents
    -1.05
    POSITIVE LOGITS
    <bos>
    1.07
    ’
    0.49
    ”.
    0.47
     #
    0.45
     Zivil
    0.44
    Jeografia
    0.44
     rapide
    0.43
     forme
    0.43
     taget
    0.43
    ("-",
    0.43
    Activations Density 1.421%

    No Known Activations