© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14164
    Prev
    Next
    INDEX
    Explanations

    words and phrases suggesting secrecy and hidden actions

    oai_token-act-pair · gemini-2.0-flash

    secrecy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    NullException
    -0.54
    شوف
    -0.50
    CppCodeGen
    -0.47
    chapter
    -0.47
     paramInt
    -0.46
     defendant
    -0.46
     Defendant
    -0.46
     chapter
    -0.46
     manuale
    -0.46
     súng
    -0.45
    POSITIVE LOGITS
     secretly
    0.86
    Tikang
    0.73
     quietly
    0.72
     hidden
    0.71
     raiſ
    0.68
     subtle
    0.65
    __":
    0.65
     deſt
    0.65
     fhew
    0.65
    UrlResolution
    0.65
    Activations Density 1.937%

    No Known Activations