© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7094
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to criminal justice, abuse, and prisons.

    oai_token-act-pair · gemini-2.0-flash

    criminal

    np_max-act-logits · gemini-2.0-flash

    terms related to criminal justice

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AlterField
    -0.63
    RemoteException
    -0.47
     الحره
    -0.46
    abetta
    -0.44
    hdysval
    -0.44
    IonicModule
    -0.44
    canestro
    -0.43
     ehe
    -0.42
    őben
    -0.42
     bergabung
    -0.42
    POSITIVE LOGITS
     AssemblyTitle
    0.57
     bezeichneter
    0.56
     CreateTagHelper
    0.56
     Wię
    0.56
     autorytatywna
    0.54
     initComponents
    0.54
     matter
    0.54
    enumi
    0.54
    ViewFeatures
    0.52
    ardless
    0.52
    Activations Density 0.928%

    No Known Activations