© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13135
    Prev
    Next
    INDEX
    Explanations

    words and phrases relating to conflict, punishment, restrictions, or pronouncements of guilt.

    oai_token-act-pair · gemini-2.0-flash

    Conflicts and consequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    KommentareTeilen
    -0.77
     getItemId
    -0.74
    ंदीखरीदारी
    -0.72
    ruptedException
    -0.69
    CloseOperation
    -0.65
    IntoConstraints
    -0.61
    findpost
    -0.60
    SequentialGroup
    -0.59
    ="@+
    -0.59
     handleMessage
    -0.59
    POSITIVE LOGITS
    Lähteet
    0.50
    Aiheesta
    0.48
     region
    0.48
     gimbal
    0.47
    Története
    0.46
    BRACK
    0.46
     lading
    0.46
     compare
    0.45
     esternos
    0.45
     yana
    0.44
    Activations Density 0.277%

    No Known Activations