© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8122
    Prev
    Next
    INDEX
    Explanations

    a person saying something and another person either continuing or adding to the point

    oai_token-act-pair · gemini-2.0-flash

    quotation mark or added

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    timis
    -0.48
     لدي
    -0.46
     Assemble
    -0.46
     ''),
    -0.46
    leness
    -0.46
     informée
    -0.45
     ""),
    -0.44
     Duckworth
    -0.44
     Naomi
    -0.44
     utafiti
    -0.44
    POSITIVE LOGITS
    Personendaten
    0.72
     CreateTagHelper
    0.70
    AlterField
    0.63
     Réponses
    0.63
     للمعارف
    0.60
     Taktlose
    0.59
    ScopeManager
    0.57
     betweenstory
    0.55
     незавершена
    0.53
    setArguments
    0.53
    Activations Density 0.220%

    No Known Activations