© 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. 12653
    Prev
    Next
    INDEX
    Explanations

    elements of sentence parsing, including dependencies, subjects, and objects

    oai_token-act-pair · gemini-2.0-flash

    parsing and language processing

    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
    Express
    -0.66
     Express
    -0.62
     expres
    -0.62
     express
    -0.61
    express
    -0.57
    image
    -0.56
    MemoryWarning
    -0.56
     expresses
    -0.56
     uttry
    -0.54
     melu
    -0.51
    POSITIVE LOGITS
    EDEFAULT
    0.79
    ThroughAttribute
    0.71
    afficheront
    0.69
    ----</
    0.68
     Réponses
    0.67
     دیکھیے
    0.67
     متعلقه
    0.66
    tonode
    0.66
     Efq
    0.65
    timewa
    0.65
    Activations Density 3.036%

    No Known Activations