© 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. 14454
    Prev
    Next
    INDEX
    Explanations

    Java code

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "class"

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

    Code class

    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
    ngrx
    -0.39
    bibitem
    -0.38
    TeX
    -0.36
    нию
    -0.36
    (*
    -0.35
     daher
    -0.34
    नलिखित
    -0.34
     SQLITE
    -0.33
    ges
    -0.33
    uffff
    -0.33
    POSITIVE LOGITS
     class
    3.44
    class
    3.05
     classes
    2.78
     classe
    2.52
     Class
    2.44
     Classes
    2.33
    Class
    2.33
     CLASS
    2.30
     clase
    2.27
    classes
    2.23
    Activations Density 3.312%

    No Known Activations