© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2111
    Prev
    Next
    INDEX
    Explanations

    words related to safeguards and shelter

    oai_token-act-pair · gemini-2.0-flash

    Escape, protection from something bad

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     proprietà
    -0.49
     BnF
    -0.49
    vece
    -0.48
    PrototypeOf
    -0.46
     presenza
    -0.46
    HasAnnotation
    -0.46
     piattaforma
    -0.45
     seguido
    -0.45
     échange
    -0.45
     AssemblyTitle
    -0.44
    POSITIVE LOGITS
    原始内容存档于
    0.64
     Außen
    0.57
    DockStyle
    0.54
    :][
    0.54
     ')[
    0.54
    WebVitals
    0.53
    tvguidetime
    0.53
    bootstrapcdn
    0.53
     "','
    0.52
    外部連結
    0.52
    Activations Density 9.041%

    No Known Activations