© 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. 15715
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to winter holidays and traditions.

    oai_token-act-pair · gemini-2.0-flash

    holiday

    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
    ditionally
    -0.57
    STATUS
    -0.46
     dare
    -0.45
     Sim
    -0.43
    Status
    -0.43
    kh
    -0.42
    #+#
    -0.42
    gj
    -0.42
     estatus
    -0.42
     traditionally
    -0.42
    POSITIVE LOGITS
     BoxFit
    0.84
     esternos
    0.79
    ftagPool
    0.78
    StoryboardSegue
    0.76
    ]='\
    0.71
     Chwiliwch
    0.70
    تقاوى
    0.68
    ChildScrollView
    0.67
     فريبيس
    0.66
    anthene
    0.66
    Activations Density 2.412%

    No Known Activations