© 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. 5405
    Prev
    Next
    INDEX
    Explanations

    code snippets including comments, print statements, and various code structures

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    complexContent
    -0.75
    WriteBarrier
    -0.65
     tomber
    -0.50
    Sharp
    -0.50
    ".
    -0.50
    addCriterion
    -0.50
     pintadas
    -0.50
     "]";
    -0.49
    ConfigureAwait
    -0.48
     françaises
    -0.48
    POSITIVE LOGITS
    +#+#
    0.70
    IntoConstraints
    0.61
     насељу
    0.60
    posedge
    0.56
    fromnode
    0.54
    WriteTagHelper
    0.54
    CompleteListener
    0.54
     saites
    0.52
    Autoritní
    0.52
     esboço
    0.51
    Activations Density 2.103%

    No Known Activations