© 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. 15060
    Prev
    Next
    INDEX
    Explanations

    words related to programming, especially iteration and variables

    oai_token-act-pair · gemini-2.0-flash

    words with special characters and formatting

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

    foreign language words

    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
    ,
    -0.75
    tip
    -0.64
     
    -0.64
    .
    -0.61
    <eos>
    -0.60
    ↵↵
    -0.59
     (
    -0.57
     “
    -0.57
    ...
    -0.56
    -
    -0.55
    POSITIVE LOGITS
     Efq
    1.38
     myſelf
    1.27
     Monfieur
    1.26
     ſeveral
    1.24
     itſelf
    1.17
     whoſe
    1.16
     faſt
    1.16
     Diſ
    1.16
     Majefty
    1.14
     Anſ
    1.12
    Activations Density 0.364%

    No Known Activations