© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5452
    Prev
    Next
    INDEX
    Explanations

    the word "according" and the fragment "aff"

    oai_token-act-pair · gemini-2.0-flash

    according

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     according
    -2.34
    according
    -2.06
    <bos>
    -1.98
    According
    -1.89
     According
    -1.74
     selon
    -1.58
     según
    -1.52
     ACCORD
    -1.40
     volgens
    -1.40
     menurut
    -1.37
    POSITIVE LOGITS
    sidemargin
    0.78
     "..\..\
    0.65
    enumi
    0.64
     []:
    0.62
    ienze
    0.60
    addContainerGap
    0.60
    HomeAsUpEnabled
    0.60
    Ƚ
    0.59
    borderSide
    0.59
     protoimpl
    0.57
    Activations Density 0.741%

    No Known Activations