© 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. 9700
    Prev
    Next
    INDEX
    Explanations

    instances of someone sneaking

    oai_token-act-pair · gemini-2.0-flash

    silence and secrecy

    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
    GEBURTSDATUM
    -0.74
    AccessorTable
    -0.63
    Personensuche
    -0.63
    TagMode
    -0.63
     незавершена
    -0.62
    principalTable
    -0.59
     AssemblyCulture
    -0.58
     memer
    -0.57
    MemoryWarning
    -0.56
    tonode
    -0.52
    POSITIVE LOGITS
     silent
    1.64
     silently
    1.63
     stealth
    1.59
     quietly
    1.56
     secret
    1.50
     hidden
    1.50
     secretly
    1.46
     sneaky
    1.42
    silent
    1.40
    Silent
    1.38
    Activations Density 1.332%

    No Known Activations