© 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. 4517
    Prev
    Next
    INDEX
    Explanations

    parts of British place names

    oai_token-act-pair · gemini-2.0-flash

    English place names

    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
    ICOLON
    -0.53
    EndContext
    -0.52
    Mockito
    -0.52
    TabIndex
    -0.52
     initComponents
    -0.51
    procs
    -0.50
     localObject
    -0.48
    Parcelize
    -0.48
    достатки
    -0.47
    golang
    -0.46
    POSITIVE LOGITS
     Biôgrafia
    0.66
     Paglinawan
    0.65
    AndEndTag
    0.63
    脚注の使い方
    0.58
     externi
    0.57
     ―――――
    0.56
    GraphicsUnit
    0.56
    RectangleBorder
    0.56
    utriche
    0.55
     CreateTagHelper
    0.54
    Activations Density 0.471%

    No Known Activations