© 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. 10855
    Prev
    Next
    INDEX
    Explanations

    words related to comparing large or small quantities, often in the context of fractions or politics

    oai_token-act-pair · gemini-2.0-flash

    adjectives describing size

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

    size related

    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
     Majefty
    -0.69
    addCriterion
    -0.69
    SourceChecksum
    -0.66
    Mid
    -0.63
     poffe
    -0.60
    TintMode
    -0.58
     Chriftian
    -0.58
     mittleren
    -0.58
     habet
    -0.58
    EndGlobalSection
    -0.57
    POSITIVE LOGITS
     old
    1.03
     small
    1.02
     large
    0.92
     tall
    0.85
     big
    0.85
    small
    0.83
     young
    0.82
     tiny
    0.81
     very
    0.80
     cheap
    0.79
    Activations Density 4.705%

    No Known Activations