© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4645
    Prev
    Next
    INDEX
    Explanations

    words about defending against threats

    oai_token-act-pair · gemini-2.0-flash

    fighting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ffey
    -0.54
     חיצוניים
    -0.53
     tölt
    -0.51
    μβρίου
    -0.50
     getRule
    -0.49
     appropriation
    -0.49
     board
    -0.48
    rylic
    -0.48
     appropri
    -0.48
    unjuk
    -0.48
    POSITIVE LOGITS
    <bos>
    1.00
    ajuato
    0.69
     fought
    0.68
    fighting
    0.64
    ✨:
    0.63
    PhysRev
    0.63
    Fighting
    0.62
     fighting
    0.59
     combating
    0.58
     enfrent
    0.57
    Activations Density 1.222%

    No Known Activations