© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15807
    Prev
    Next
    INDEX
    Explanations

    words with seemingly Danish or Scandinavian origin in movie titles

    oai_token-act-pair · gemini-2.0-flash

    en

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    ValueStyle
    -0.85
    
    -0.78
     صوتيه
    -0.74
    >>;
    -0.71
    irtschaft
    -0.71
    extAlignment
    -0.69
    NewUrlParser
    -0.68
    enumii
    -0.67
    ]='\
    -0.66
    šinou
    -0.65
    POSITIVE LOGITS
    Xna
    0.58
    xaml
    0.55
    omia
    0.53
     goma
    0.53
     hura
    0.53
     durs
    0.53
    meanor
    0.52
     kalan
    0.51
    อด
    0.50
    ···
    0.50
    Activations Density 0.195%

    No Known Activations