© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6817
    Prev
    Next
    INDEX
    Explanations

    phrases and words about caring and positive sentiment

    oai_token-act-pair · gemini-2.0-flash

    forms of the verb 'hold'

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

    hold

    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
    setVerticalGroup
    -0.87
     незавершена
    -0.82
    MigrationBuilder
    -0.75
     myſelf
    -0.74
     tartalomajánló
    -0.69
    Архівовано
    -0.68
    LoggerFactory
    -0.67
    titleMargin
    -0.66
     referenties
    -0.66
     resourceCulture
    -0.66
    POSITIVE LOGITS
     hold
    0.88
     held
    0.86
     Hold
    0.78
     holds
    0.77
    hold
    0.77
    held
    0.76
     holding
    0.69
    Hold
    0.66
    holds
    0.62
     Held
    0.62
    Activations Density 1.294%

    No Known Activations