© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12614
    Prev
    Next
    INDEX
    Explanations

    the word "So"

    oai_token-act-pair · gemini-2.0-flash

    token 'So' followed by various question words or additional phrases

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

    Starting a sentence

    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
    numerusform
    -0.49
    #+#
    -0.44
    ----</
    -0.43
     susi
    -0.41
    гово
    -0.40
    fold
    -0.39
     Those
    -0.39
     woll
    -0.39
    Well
    -0.39
    >*/
    -0.38
    POSITIVE LOGITS
     far
    0.98
     långt
    0.73
    jauh
    0.73
     why
    0.71
    AndEndTag
    0.70
    ViewImports
    0.68
     NSCoder
    0.68
     how
    0.68
    EndInit
    0.67
    FormTagHelper
    0.67
    Activations Density 1.333%

    No Known Activations