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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7286
    Prev
    Next
    INDEX
    Explanations

    qualifying adverbs and adjectives, particularly "relatively"

    oai_token-act-pair · gemini-2.0-flash

    expressions indicating relativity or comparison

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

    relatively

    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
     somewhat
    -0.85
    Datuak
    -0.84
    Somewhat
    -0.75
    somewhat
    -0.73
    relatively
    -0.73
     relatively
    -0.71
    RectangleBorder
    -0.70
    InjectAttribute
    -0.70
     Signalez
    -0.67
     Somewhat
    -0.66
    POSITIVE LOGITS
    CrossRef
    0.67
     كورة
    0.53
     harmless
    0.52
    Successful
    0.50
     equals
    0.50
     everywhere
    0.50
     kyse
    0.48
    }`).
    0.48
    ngths
    0.48
    ych
    0.48
    Activations Density 4.584%

    No Known Activations