© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1847
    Prev
    Next
    INDEX
    Explanations

    certain names, possibly South African

    oai_token-act-pair · gemini-2.0-flash

    legal proceedings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ForResult
    -0.61
     Gegenteil
    -0.56
    DrawerToggle
    -0.49
    numerusform
    -0.49
    mistic
    -0.49
    IsContent
    -0.49
     HttpNotFound
    -0.49
    Jegyzetek
    -0.48
    companied
    -0.47
    sphinx
    -0.47
    POSITIVE LOGITS
     disambiguazione
    0.60
     Nigerians
    0.59
     Nigeria
    0.56
    SharedDtor
    0.56
     Nigerian
    0.54
    نگار
    0.53
    Nigeria
    0.51
    Nigerian
    0.50
    Crunch
    0.50
    feuille
    0.50
    Activations Density 0.114%

    No Known Activations