© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12753
    Prev
    Next
    INDEX
    Explanations

    filler words that don't contribute a lot to the meaning of phrases, such as "to," "by," "in," "on," "of," and articles

    oai_token-act-pair · gemini-2.0-flash

    quoted text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     سبتمبر
    -0.63
    :{}
    -0.58
    Carriera
    -0.57
    Παραπομπές
    -0.57
     }}">
    -0.57
    :(
    -0.57
    achev
    -0.57
    =('
    -0.56
    matchCondition
    -0.56
     CURIAM
    -0.56
    POSITIVE LOGITS
     myſelf
    0.55
     itſelf
    0.53
     pngtree
    0.52
     Cæsar
    0.52
     faſt
    0.51
     Monfieur
    0.49
     étoient
    0.48
     pleaſure
    0.47
     utafitiHapana
    0.46
    <bos>
    0.46
    Activations Density 15.125%

    No Known Activations