© 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. 6694
    Prev
    Next
    INDEX
    Explanations

    capital letters followed by close parentheses, or words related to computer code

    oai_token-act-pair · gemini-2.0-flash

    figures and labels

    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
    UserScript
    -0.86
     CreateTagHelper
    -0.80
    ContentAsync
    -0.74
    ValueStyle
    -0.74
     useAppContext
    -0.73
     NSCoder
    -0.71
     متعلقه
    -0.67
    KommentareTeilen
    -0.66
    RetentionPolicy
    -0.65
    TagMode
    -0.62
    POSITIVE LOGITS
     EF
    1.02
     AF
    1.02
    GF
    1.02
     MF
    1.01
     PF
    1.00
    CF
    1.00
    SF
    1.00
     CF
    1.00
     FR
    0.99
    UF
    0.99
    Activations Density 27.363%

    No Known Activations