© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10906
    Prev
    Next
    INDEX
    Explanations

    words related to scientific studies and measurements

    oai_token-act-pair · gemini-2.0-flash

    scientific measurements/results

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    each
    -0.48
    indd
    -0.45
     EACH
    -0.42
    รม
    -0.41
    inguém
    -0.40
    서는
    -0.40
     reprodução
    -0.40
    behörde
    -0.39
    зора
    -0.39
    都不
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    1.05
     gynhyrchwyd
    0.85
    PreferredItem
    0.78
    <bos>
    0.74
     pinulongan
    0.72
     kaarangay
    0.72
     doInBackground
    0.72
    TargetException
    0.71
    Autoritní
    0.71
     fuper
    0.69
    Activations Density 3.300%

    No Known Activations