© 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. 12075
    Prev
    Next
    INDEX
    Explanations

    words related to making decisions, feelings, and sewing

    oai_token-act-pair · gemini-2.0-flash

    the word 'for'

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

    "for" in other languages

    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
    KommentareTeilen
    -0.81
     onOptions
    -0.78
    aarrggbb
    -0.76
     '\\;'
    -0.73
    âce
    -0.69
     يتيمه
    -0.68
    enderror
    -0.67
    CppMethod
    -0.66
     nakalista
    -0.64
     ſeveral
    -0.64
    POSITIVE LOGITS
     for
    2.84
    for
    1.91
     для
    1.72
     voor
    1.61
     untuk
    1.55
     für
    1.52
     For
    1.48
     FOR
    1.48
     برای
    1.43
     för
    1.41
    Activations Density 9.844%

    No Known Activations