© 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. 5426
    Prev
    Next
    INDEX
    Explanations

    technical descriptions, measurements, apparatus and/or instruments, and schematics.

    oai_token-act-pair · gemini-2.0-flash

    Size

    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
     pauvres
    -0.51
     attaques
    -0.50
     fédé
    -0.48
     jurí
    -0.47
     judicia
    -0.45
    šlo
    -0.45
    offrir
    -0.45
     økonom
    -0.44
     tóxic
    -0.44
     honlap
    -0.44
    POSITIVE LOGITS
    protoimpl
    0.90
    WriteTagHelper
    0.85
    ControllerAdvice
    0.75
    .*")]
    0.74
    ruptedException
    0.73
     invokingState
    0.71
     kaarangay
    0.71
    ArrowToggle
    0.70
    djangoproject
    0.70
    UnknownFieldSet
    0.69
    Activations Density 19.047%

    No Known Activations