© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12595
    Prev
    Next
    INDEX
    Explanations

    helper verbs and related words

    oai_token-act-pair · gemini-2.0-flash

    take

    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
    DockStyle
    -0.70
    UrlResolution
    -0.54
    ResponseWriter
    -0.52
     ujednoznacz
    -0.52
     Dependence
    -0.51
    NavigationView
    -0.51
     Kram
    -0.51
     flushed
    -0.50
    futbolista
    -0.48
     Curitiba
    -0.47
    POSITIVE LOGITS
     take
    1.61
    take
    1.60
    Take
    1.55
     Take
    1.54
     taking
    1.52
    TAKE
    1.50
    taking
    1.50
     Taking
    1.45
     TAKE
    1.44
    Taking
    1.42
    Activations Density 1.632%

    No Known Activations