© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13952
    Prev
    Next
    INDEX
    Explanations

    harsh or vulgar language

    oai_token-act-pair · gemini-2.0-flash

    Law enforcement contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     police
    -2.25
     Police
    -2.06
    police
    -2.05
    Police
    -1.98
     POLICE
    -1.91
     policemen
    -1.57
     policeman
    -1.55
     Polize
    -1.45
    警察
    -1.44
     policing
    -1.42
    POSITIVE LOGITS
     GenerationType
    0.81
     initComponents
    0.74
     autorytatywna
    0.67
     beginnetje
    0.61
     незавершена
    0.60
     يتيمه
    0.60
    complexContent
    0.59
    rungsseite
    0.58
    ViewFeatures
    0.57
     BoxDecoration
    0.57
    Activations Density 1.672%

    No Known Activations