© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5117
    Prev
    Next
    INDEX
    Explanations

    the word "escape"

    oai_token-act-pair · gemini-2.0-flash

    escape

    np_max-act · gemini-2.0-flash

    escape Method used: 1 — because every top token is "escape" — escape

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    IndentedString
    -0.90
     مشين
    -0.83
     հղումներ
    -0.82
    RegressionTest
    -0.82
    WithMany
    -0.79
    VolleyError
    -0.78
      (
    -0.78
    Спољашње
    -0.78
    IUrlHelper
    -0.77
    SequentialGroup
    -0.76
    POSITIVE LOGITS
    Опис
    0.48
     ++)
    0.48
    most
    0.47
    ">:
    0.46
     dafür
    0.46
    ↵↵
    0.46
    řed
    0.45
     Conno
    0.45
    theless
    0.45
     most
    0.45
    Activations Density 1.269%

    No Known Activations