© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 14038
    Prev
    Next
    INDEX
    Explanations

    proper nouns names of organizations and places

    oai_token-act-pair · gemini-2.0-flash

    places

    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
    expandindo
    -0.84
    StoryboardSegue
    -0.81
     otomatig
    -0.76
     defaultstate
    -0.76
    EDEFAULT
    -0.71
    UIControlState
    -0.69
     ModelExpression
    -0.69
    DeleteBehavior
    -0.68
    
    -0.65
    parsedMessage
    -0.64
    POSITIVE LOGITS
     Justiça
    0.45
     pomy
    0.43
    synchronize
    0.42
    JOptionPane
    0.41
     pinulongan
    0.41
     Privacidad
    0.40
     written
    0.40
    rrh
    0.38
     jegy
    0.38
    Maximize
    0.38
    Activations Density 1.650%

    No Known Activations