© 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. 15187
    Prev
    Next
    INDEX
    Explanations

    words describing something or providing additional information

    oai_token-act-pair · gemini-2.0-flash

    defining/explaining

    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
     prochaines
    -0.47
    पया
    -0.44
    teaching
    -0.43
    puh
    -0.43
     bây
    -0.42
    (?)
    -0.41
     mers
    -0.41
    ейчас
    -0.41
    шного
    -0.41
     katanya
    -0.41
    POSITIVE LOGITS
    <bos>
    0.96
    InjectAttribute
    0.84
     notably
    0.73
    besondere
    0.71
    Biografía
    0.68
    verwijspagina
    0.68
     notamment
    0.68
    ostante
    0.65
    RegistryLite
    0.64
    Apesar
    0.63
    Activations Density 1.517%

    No Known Activations