© 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. 14184
    Prev
    Next
    INDEX
    Explanations

    words and patterns of text that look like human conversation, reasoning, and opinion giving, as well as verbs

    oai_token-act-pair · gemini-2.0-flash

    adverbs indicating thoughtful actions

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

    adverbs

    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
     quelcon
    -0.77
     naturelles
    -0.74
     récents
    -0.73
     russes
    -0.72
     élevés
    -0.72
     élevées
    -0.72
     łat
    -0.72
     vectorielles
    -0.71
     rapides
    -0.71
     positivas
    -0.69
    POSITIVE LOGITS
     creatively
    0.73
     sensibly
    0.71
     tentatively
    0.71
     controversi
    0.69
     produ
    0.69
     meaningfully
    0.68
     smartly
    0.67
     omin
    0.66
     responsibly
    0.66
     solemnly
    0.66
    Activations Density 4.614%

    No Known Activations