© 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. 13807
    Prev
    Next
    INDEX
    Explanations

    text from terms of service or shipping documentation

    oai_token-act-pair · gemini-2.0-flash

    period

    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
    contentLoaded
    -0.60
    ranton
    -0.50
     SqlCommand
    -0.46
    batis
    -0.44
    esez
    -0.43
    ̍t
    -0.43
    InjectAttribute
    -0.42
    expandindo
    -0.42
     journey
    -0.42
    /******/
    -0.41
    POSITIVE LOGITS
    AutoScaleMode
    0.69
     remercier
    0.61
     initComponents
    0.61
    Jeografia
    0.60
     doigt
    0.59
    InSection
    0.59
    endpush
    0.58
    viewDidLoad
    0.58
    paravant
    0.58
     préc
    0.58
    Activations Density 6.490%

    No Known Activations