© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8221
    Prev
    Next
    INDEX
    Explanations

    biased political rhetoric.

    oai_token-act-pair · gemini-2.0-flash

    expose truth

    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
     صوتيه
    -0.98
     defaultstate
    -0.88
    StoryboardSegue
    -0.86
    Datuak
    -0.85
     فريبيس
    -0.82
     متعلقه
    -0.81
    IndentedString
    -0.81
    contentLoaded
    -0.80
     Мексичка
    -0.79
    ImageContext
    -0.79
    POSITIVE LOGITS
     expose
    0.77
     truth
    0.72
     exposed
    0.67
     Truth
    0.66
     exposes
    0.66
     exposing
    0.66
     True
    0.64
     true
    0.64
     exposé
    0.62
     TRUTH
    0.61
    Activations Density 4.721%

    No Known Activations