© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12143
    Prev
    Next
    INDEX
    Explanations

    the string "tor" as a prefix

    oai_token-act-pair · gemini-2.0-flash

    tor

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Demografia
    -0.59
    arted
    -0.52
     Wayback
    -0.52
     Thore
    -0.49
     Crusoe
    -0.49
    arit
    -0.48
     PKK
    -0.47
    zzar
    -0.45
    Viitteet
    -0.45
     taka
    -0.44
    POSITIVE LOGITS
    HandlerContext
    0.69
    fromnode
    0.64
    UnusedPrivate
    0.62
    Spoljašnje
    0.60
     createSlice
    0.59
    principalTable
    0.58
    abestanden
    0.55
    GraphicsUnit
    0.55
     otomatig
    0.54
    Datuak
    0.53
    Activations Density 0.373%

    No Known Activations