© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5810
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ing' or starting with prefixes 'under', or 'inter', as well as the word 'pin'

    oai_token-act-pair · gemini-2.0-flash

    business

    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
     nakalista
    -0.66
     picioare
    -0.57
     cytoplasm
    -0.55
     AttributeSet
    -0.54
     rând
    -0.53
     urbanos
    -0.51
    WithMany
    -0.50
     Chara
    -0.49
     "..\..\
    -0.49
     Dorian
    -0.49
    POSITIVE LOGITS
    <bos>
    0.86
    Portail
    0.77
     محفوظة
    0.70
    enderror
    0.67
    */
    0.65
    '));
    0.63
    ']],
    0.62
    脚注の使い方
    0.61
    "])){
    0.60
    "]]
    0.59
    Activations Density 1.914%

    No Known Activations