© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6356
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to fishing trips

    oai_token-act-pair · gemini-2.0-flash

    Mercury engines and fishing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     lure
    -0.67
     attract
    -0.65
     angler
    -0.65
     attraction
    -0.64
     attracting
    -0.63
     viewDidLoad
    -0.60
     attracts
    -0.56
    FieldError
    -0.54
     bait
    -0.54
    Attra
    -0.54
    POSITIVE LOGITS
    addGap
    0.68
    SequentialGroup
    0.56
    FormTagHelper
    0.56
    脚注の使い方
    0.56
    олові
    0.55
     للاسماء
    0.55
     dAtA
    0.54
    ership
    0.54
    Xna
    0.54
     StatelessWidget
    0.53
    Activations Density 0.227%

    No Known Activations