© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13589
    Prev
    Next
    INDEX
    Explanations

    words used in arguments or discussions

    oai_token-act-pair · gemini-2.0-flash

    opinions, judgements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     albeit
    -0.68
     Però
    -0.68
    はある
    -0.68
    Portail
    -0.67
    ではある
    -0.66
    findpost
    -0.66
    albeit
    -0.65
     itſelf
    -0.65
     hoor
    -0.63
     lakini
    -0.62
    POSITIVE LOGITS
    zubauen
    0.49
    peur
    0.47
    peutic
    0.45
    іга
    0.45
    ----</
    0.44
    Unmarshal
    0.43
    OwnProperty
    0.43
     therefore
    0.43
    cox
    0.42
    himovic
    0.42
    Activations Density 4.768%

    No Known Activations