© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6766
    Prev
    Next
    INDEX
    Explanations

    chunks of source code

    oai_token-act-pair · gemini-2.0-flash

    proxy servers and interfaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     typically
    -0.46
     sport
    -0.46
     Foundation
    -0.45
    antia
    -0.44
    пі
    -0.43
    messe
    -0.43
     subject
    -0.42
    formis
    -0.42
     angele
    -0.41
     par
    -0.41
    POSITIVE LOGITS
    <bos>
    1.22
    RegressionTest
    0.87
    djangoproject
    0.86
    EndGlobalSection
    0.84
    ########.
    0.83
    featureID
    0.83
    InitVars
    0.81
     hObject
    0.77
     doInBackground
    0.77
    elemField
    0.77
    Activations Density 3.412%

    No Known Activations