© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6315
    Prev
    Next
    INDEX
    Explanations

    words relating to geographic locations and routes

    oai_token-act-pair · gemini-2.0-flash

    diverse terrain names

    np_token-act-pair-logits · gpt-4o-mini

    Diverse mixed-content documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     ModelExpression
    -0.98
    ArrowToggle
    -0.96
    DockStyle
    -0.84
     bezeichneter
    -0.75
     بيها
    -0.71
     pinulongan
    -0.69
    "]));
    -0.68
    homonymie
    -0.68
     ujednoznacz
    -0.66
     InputDecoration
    -0.65
    POSITIVE LOGITS
     оби
    0.42
    itsi
    0.41
     lit
    0.41
     see
    0.40
     appreciate
    0.39
     fo
    0.39
    MathML
    0.38
    ব
    0.38
    felt
    0.38
    Peacock
    0.38
    Activations Density 0.516%

    No Known Activations