© 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. 12521
    Prev
    Next
    INDEX
    Explanations

    words related to legality and business, particularly about not hiring

    oai_token-act-pair · gemini-2.0-flash

    is

    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
     oprot
    -0.68
     esternos
    -0.66
    EDEFAULT
    -0.63
     InputDecoration
    -0.63
     "..\..\
    -0.62
    styleType
    -0.62
    setVerticalGroup
    -0.60
    migrationBuilder
    -0.58
    astéroïdes
    -0.57
    UseVisualStyle
    -0.54
    POSITIVE LOGITS
     Lordships
    0.53
    arrol
    0.50
    nics
    0.49
     myſelf
    0.49
    haustible
    0.49
    Instru
    0.47
    ftances
    0.47
     Majefty
    0.47
    wiſe
    0.47
    leſs
    0.46
    Activations Density 1.882%

    No Known Activations