© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14943
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with military operations, defense, or government response to threats, sometimes including dates or locations related to military activity

    oai_token-act-pair · gemini-2.0-flash

    reconnaissance and military topics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     Administrativna
    -0.47
    boretum
    -0.44
    وصلات
    -0.43
     кислота
    -0.43
    setLayoutManager
    -0.42
    renderItem
    -0.42
    useEffect
    -0.42
    ceau
    -0.41
     James
    -0.40
    Życiorys
    -0.40
    POSITIVE LOGITS
    GOTREF
    0.84
    AndEndTag
    0.82
    ChildScrollView
    0.63
     MotionEvent
    0.62
    protoimpl
    0.60
    Personensuche
    0.59
     PSR
    0.59
     resourceCulture
    0.56
     Spain
    0.55
    SBATCH
    0.55
    Activations Density 18.251%

    No Known Activations