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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8441
    Prev
    Next
    INDEX
    Explanations

    a variety of common words, possibly indicating poor training data

    oai_token-act-pair · gemini-2.0-flash

    have

    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
    تقاوى
    -0.62
    rungsseite
    -0.55
    ScopeManager
    -0.52
    SequentialGroup
    -0.50
     protoimpl
    -0.48
    `;
    -0.47
     HasFactory
    -0.46
    runApp
    -0.46
    ]</
    -0.44
    WebServlet
    -0.44
    POSITIVE LOGITS
     have
    1.75
    have
    1.53
    Have
    1.51
     Have
    1.40
     HAVE
    1.22
    HAVE
    1.15
     haben
    1.07
     hebben
    1.01
     haue
    1.00
     hanno
    0.94
    Activations Density 4.394%

    No Known Activations