© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9991
    Prev
    Next
    INDEX
    Explanations

    sections of Java code

    oai_token-act-pair · gemini-2.0-flash

    void

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    utilisons
    -0.57
    ENESS
    -0.49
     Californie
    -0.48
    енча
    -0.47
    verwijspagina
    -0.47
     amal
    -0.44
    atchewan
    -0.43
    รวจ
    -0.42
    OrEqualTo
    -0.42
    ISupport
    -0.42
    POSITIVE LOGITS
    migrationBuilder
    0.66
    WebVitals
    0.61
     سكان
    0.61
     rospy
    0.59
    AutoField
    0.58
     onPostExecute
    0.57
    ($__
    0.57
    UITableView
    0.56
    AnimationsModule
    0.56
     defaultstate
    0.56
    Activations Density 0.105%

    No Known Activations