© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13412
    Prev
    Next
    INDEX
    Explanations

    the partial word "char" when it's part of a longer word

    oai_token-act-pair · gemini-2.0-flash

    char

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     Efq
    -1.38
     myſelf
    -1.29
     Houſe
    -1.26
     Majefty
    -1.26
     houſe
    -1.23
     purpoſe
    -1.19
     ſeveral
    -1.18
     ―――――
    -1.17
     ſtate
    -1.17
    ſelf
    -1.17
    POSITIVE LOGITS
    R
    0.98
    T
    0.97
    W
    0.94
    B
    0.93
    D
    0.93
    F
    0.93
    The
    0.91
    C
    0.91
    L
    0.90
    1
    0.89
    Activations Density 0.410%

    No Known Activations