© 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. 15261
    Prev
    Next
    INDEX
    Explanations

    code snippets including variable assignments, class declarations or http requests

    oai_token-act-pair · gemini-2.0-flash

    target

    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
    <bos>
    -1.76
    printStackTrace
    -0.70
    SizeF
    -0.56
     fuf
    -0.55
     useDispatch
    -0.53
    StreetMap
    -0.51
     springfox
    -0.51
    uxxxx
    -0.50
    /*
    -0.50
     tqdm
    -0.49
    POSITIVE LOGITS
     étoit
    0.73
     gezet
    0.68
    ISupport
    0.65
    المناصب
    0.64
     inspiradoras
    0.64
     blessés
    0.62
     mourut
    0.61
     actuels
    0.61
    lowa
    0.60
    DropTable
    0.60
    Activations Density 1.475%

    No Known Activations