© 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. 6553
    Prev
    Next
    INDEX
    Explanations

    argumentative writing

    oai_token-act-pair · gemini-2.0-flash

    alternatives or contrasts

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

    instead

    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
     aren
    -0.69
     isn
    -0.68
     wasn
    -0.65
     Wasn
    -0.63
     beginnetje
    -0.62
    wasn
    -0.62
     weren
    -0.62
     ain
    -0.61
     aint
    -0.61
     arent
    -0.60
    POSITIVE LOGITS
     instead
    1.21
    instead
    1.05
    Instead
    1.05
     Instead
    1.02
    +#+#
    0.92
     rather
    0.83
    而不是
    0.79
     вместо
    0.75
     invece
    0.73
    rather
    0.70
    Activations Density 3.521%

    No Known Activations