© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7955
    Prev
    Next
    INDEX
    Explanations

    language related to college admissions

    oai_token-act-pair · gemini-2.0-flash

    Universities/students

    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
    IntoConstraints
    -0.91
     ContentValues
    -0.65
    RegistryLite
    -0.59
    })();
    -0.59
    onViewCreated
    -0.59
    舺
    -0.59
    WebServlet
    -0.57
     hasNext
    -0.57
     <>",
    -0.55
    Viitteet
    -0.54
    POSITIVE LOGITS
     estimés
    0.50
    núť
    0.50
    ník
    0.47
     Man
    0.47
    findpost
    0.43
    cipes
    0.43
     nahilalakip
    0.43
    TagMode
    0.43
     Hombre
    0.42
     authors
    0.42
    Activations Density 1.301%

    No Known Activations