© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15122
    Prev
    Next
    INDEX
    Explanations

    code snippets, specifically related to web development and data handling, possibly related to JSON and XML formats

    oai_token-act-pair · gemini-2.0-flash

    structured programming elements

    np_token-act-pair-logits · gpt-4o-mini

    Code and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     الحره
    -1.28
     raiſ
    -1.13
     bezeichneter
    -1.11
     MainAxisSize
    -1.09
    IntoConstraints
    -1.08
    IUrlHelper
    -1.07
     itſelf
    -1.03
     Jefus
    -1.02
     صوتيه
    -1.02
     Theſe
    -1.02
    POSITIVE LOGITS
     
    0.79
    ↵
    0.74
     A
    0.67
     (
    0.66
     S
    0.66
     I
    0.64
        
    0.64
    ,
    0.63
     s
    0.60
     T
    0.60
    Activations Density 3.722%

    No Known Activations