© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2364
    Prev
    Next
    INDEX
    Explanations

    text messages and relationship feelings, especially about an EX

    oai_token-act-pair · gemini-2.0-flash

    romantic feelings and breakups

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     Need
    -0.66
     need
    -0.60
    enumii
    -0.60
    numerusform
    -0.56
    Need
    -0.54
    WaitGroup
    -0.53
     Me
    -0.51
    need
    -0.50
    ագրություններ
    -0.50
     NEED
    -0.49
    POSITIVE LOGITS
     كومونز
    0.61
     kasarigan
    0.57
    <?
    0.55
     Italijanski
    0.55
    TacToe
    0.52
     jil
    0.51
    rrggbb
    0.50
     LCCN
    0.49
     vuitton
    0.48
     obstante
    0.47
    Activations Density 1.787%

    No Known Activations