© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2208
    Prev
    Next
    INDEX
    Explanations

    elements of formal correspondence

    oai_token-act-pair · gemini-2.0-flash

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ništ
    -0.63
    >*/
    -0.60
    DialogTitle
    -0.59
    buss
    -0.58
     HasFactory
    -0.55
    HideFlags
    -0.55
    MessageTagHelper
    -0.55
    ChromeDriver
    -0.53
    Enfant
    -0.53
    ogens
    -0.53
    POSITIVE LOGITS
    addressed
    0.56
     digress
    0.54
    UrlResolution
    0.54
     them
    0.52
     anyone
    0.50
    XtraReports
    0.50
     addressed
    0.50
    hadiran
    0.48
    œur
    0.48
     addressing
    0.46
    Activations Density 1.147%

    No Known Activations