© 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. 10764
    Prev
    Next
    INDEX
    Explanations

    the words "enemy" or "shooting"

    oai_token-act-pair · gemini-2.0-flash

    enemy, shooting

    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
    ↵
    -0.91
     
    -0.90
    ↵↵
    -0.83
    -
    -0.77
    n
    -0.77
    S
    -0.72
     /
    -0.71
    P
    -0.70
    <strong>
    -0.70
    <em>
    -0.69
    POSITIVE LOGITS
     snippetHide
    1.24
    ^(@)
    1.23
     المعيارى
    1.23
     BoxDecoration
    1.21
    RegistryLite
    1.16
    Personendaten
    1.16
     وتسجيلات
    1.16
    DockStyle
    1.15
    脚注の使い方
    1.15
    GEBURTSDATUM
    1.13
    Activations Density 0.823%

    No Known Activations