© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4368
    Prev
    Next
    INDEX
    Explanations

    technical documents related to medicine, physics, or engineering, possibly experimental

    oai_token-act-pair · gemini-2.0-flash

    Technical/scientific writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     vectorielles
    -0.87
     réguli
    -0.87
     дописавши
    -0.86
     GenerationType
    -0.86
    tagext
    -0.83
     scolaires
    -0.80
    хьтан
    -0.78
     devenus
    -0.78
     loisirs
    -0.77
     avoient
    -0.76
    POSITIVE LOGITS
     
    0.48
     he
    0.47
     up
    0.46
     Na
    0.46
     ou
    0.46
    NavController
    0.44
    go
    0.42
     around
    0.42
     together
    0.41
     ba
    0.41
    Activations Density 11.657%

    No Known Activations