© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14496
    Prev
    Next
    INDEX
    Explanations

    the phrase "Air Force"

    oai_token-act-pair · gemini-2.0-flash

    Force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     volantes
    -0.56
     rayons
    -0.56
     ruota
    -0.52
    wo
    -0.52
     sanitaires
    -0.52
     aš
    -0.51
    <&
    -0.50
     ochi
    -0.50
    SPATH
    -0.50
     razón
    -0.49
    POSITIVE LOGITS
    LookAnd
    0.91
    AndEndTag
    0.91
    UnknownFieldSet
    0.88
     initComponents
    0.87
     الحره
    0.82
    PreferredItem
    0.78
     <=",
    0.77
     <<<<<<<<<<<<<<
    0.74
    SequentialGroup
    0.68
    windowFixed
    0.67
    Activations Density 0.127%

    No Known Activations