© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5342
    Prev
    Next
    INDEX
    Explanations

    email addresses

    oai_token-act-pair · gemini-2.0-flash

    emails/usernames

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    ArrowToggle
    -0.66
     ddelweddau
    -0.64
    WriteBarrier
    -0.58
    pic
    -0.50
    ----</
    -0.49
    othesis
    -0.49
     виправивши
    -0.48
    WireFormatLite
    -0.48
    versy
    -0.48
    clist
    -0.47
    POSITIVE LOGITS
     الحره
    0.64
    AlterField
    0.61
    webElementGuid
    0.60
     judiciales
    0.56
    httphttps
    0.56
     culturelles
    0.54
    Życiorys
    0.53
     AllAfrica
    0.52
     urbanas
    0.52
     fallu
    0.51
    Activations Density 1.144%

    No Known Activations