© 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. 6375
    Prev
    Next
    INDEX
    Explanations

    words related to efficiency, advantages, or robustness in computer science or statistics

    oai_token-act-pair · gemini-2.0-flash

    terms related to efficiency and robustness

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

    data properties

    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
    }))
    -0.67
    }));
    -0.64
    TargetException
    -0.63
     initComponents
    -0.62
     Numerade
    -0.62
     bpy
    -0.61
     Lordship
    -0.60
    GEBURTSDATUM
    -0.59
    StoryboardSegue
    -0.59
    ImageContext
    -0.59
    POSITIVE LOGITS
     bajo
    0.55
     under
    0.50
     Problems
    0.49
     coefficient
    0.48
    isso
    0.47
     Challenges
    0.47
    améli
    0.46
    ExtendWith
    0.46
     problems
    0.46
    ColumnIndex
    0.45
    Activations Density 5.827%

    No Known Activations