© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8822
    Prev
    Next
    INDEX
    Explanations

    words and phrases surrounding sensitive subjects like racism, parenting, apologizing, machine problems, unwanted behavior

    oai_token-act-pair · gemini-2.0-flash

    relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     mercy
    -0.95
     forgiving
    -0.90
     apologized
    -0.86
     generous
    -0.83
     forgive
    -0.82
     grateful
    -0.82
     apologizing
    -0.79
     Forgiveness
    -0.79
     Generous
    -0.78
     merciful
    -0.77
    POSITIVE LOGITS
    Personensuche
    0.69
    stateProvider
    0.65
    oa̍t
    0.60
     nakalista
    0.60
    verwijspagina
    0.57
    hoeddwyd
    0.55
    سون
    0.55
     himo
    0.54
    MigrationBuilder
    0.54
    apunov
    0.53
    Activations Density 11.182%

    No Known Activations