© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11432
    Prev
    Next
    INDEX
    Explanations

    references to anime or japanese media

    oai_token-act-pair · gemini-2.0-flash

    Anime and manga

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     den
    -0.54
    ResumeLayout
    -0.53
    #![
    -0.51
    RenderAtEndOf
    -0.49
    printStackTrace
    -0.48
    chap
    -0.47
    BindingSource
    -0.46
    slug
    -0.45
     San
    -0.45
    MessageTagHelper
    -0.43
    POSITIVE LOGITS
    Vidite
    0.68
     ujednoznacz
    0.64
     Abp
    0.62
    abestanden
    0.61
     OFDb
    0.60
     offside
    0.60
    Personensuche
    0.60
    Notae
    0.59
    Demografie
    0.58
    ტერ
    0.58
    Activations Density 0.401%

    No Known Activations