© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4111
    Prev
    Next
    INDEX
    Explanations

    the word "as" and the word "so"

    oai_token-act-pair · gemini-2.0-flash

    as so

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     ſtate
    -1.04
     Efq
    -1.02
     purpoſe
    -1.02
    SourceChecksum
    -0.93
    enderror
    -0.93
     ſeveral
    -0.92
     ſever
    -0.91
    adaptiveStyles
    -0.91
     pleaſure
    -0.91
     ſche
    -0.90
    POSITIVE LOGITS
     does
    0.68
     will
    0.57
     would
    0.56
     too
    0.55
     do
    0.50
     can
    0.50
     did
    0.50
     
    0.49
     is
    0.49
     are
    0.47
    Activations Density 0.660%

    No Known Activations