© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6227
    Prev
    Next
    INDEX
    Explanations

    sentence fragments and informal or ungrammatical language, often including abbreviations.

    oai_token-act-pair · gemini-2.0-flash

    pas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    pyplot
    -0.68
    RegressionTest
    -0.59
    ftes
    -0.55
     akka
    -0.52
    brainly
    -0.51
    日発売
    -0.51
    mbia
    -0.50
     nakalista
    -0.49
     reasonableness
    -0.49
    ientôt
    -0.49
    POSITIVE LOGITS
     not
    1.22
     NOT
    1.16
     Not
    1.14
    Not
    1.09
    not
    1.03
    NOT
    1.02
     ikke
    0.92
     nicht
    0.87
     não
    0.82
     ikkje
    0.82
    Activations Density 1.667%

    No Known Activations