© 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. 8629
    Prev
    Next
    INDEX
    Explanations

    words and phrases that describe comparison of quantity or quality

    oai_token-act-pair · gemini-2.0-flash

    comparative adjectives indicating improvement

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

    comparative adjectives

    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
    Personendaten
    -0.85
     becauſe
    -0.81
     myſelf
    -0.81
     themſelves
    -0.79
     ſeveral
    -0.76
     Theſe
    -0.76
     незавершена
    -0.75
    expandindo
    -0.75
     uſed
    -0.75
     himſelf
    -0.73
    POSITIVE LOGITS
     better
    0.87
    better
    0.77
     Better
    0.71
     Bigger
    0.71
    Better
    0.70
     BETTER
    0.69
     hơn
    0.64
     bigger
    0.64
     greater
    0.63
     smoother
    0.60
    Activations Density 1.765%

    No Known Activations