© 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. 14633
    Prev
    Next
    INDEX
    Explanations

    phrases expressing personal feelings or thoughts

    oai_token-act-pair · gemini-2.0-flash

    superlative forms

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

    Superlative 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
     autorytatywna
    -0.82
     ujednoznacz
    -0.77
     unknownFields
    -0.77
    SourceChecksum
    -0.75
    rungsseite
    -0.74
     AssemblyCulture
    -0.72
    ագրություններ
    -0.71
     esternos
    -0.68
    Autoritní
    -0.67
    expandindo
    -0.67
    POSITIVE LOGITS
     largest
    2.06
     longest
    2.06
     greatest
    2.06
     strongest
    2.05
     fastest
    2.02
    largest
    1.98
    est
    1.93
     highest
    1.92
     hardest
    1.91
     weakest
    1.91
    Activations Density 6.005%

    No Known Activations