© 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. 15195
    Prev
    Next
    INDEX
    Explanations

    C and C++ code including the `printf` command

    oai_token-act-pair · gemini-2.0-flash

    formatted output patterns

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

    Code snippets and debugging

    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
     **/
    -0.91
     JpaRepository
    -0.84
     Jefus
    -0.83
     ―――――
    -0.80
    GEBURTSDATUM
    -0.80
     itſelf
    -0.79
     autorytatywna
    -0.79
    AndEndTag
    -0.78
    CppMethod
    -0.77
    ConstraintMaker
    -0.77
    POSITIVE LOGITS
     Ul
    0.40
     land
    0.38
     Mac
    0.38
     Pop
    0.38
    ohol
    0.37
     Off
    0.37
     والث
    0.37
    ↵
    0.36
     masing
    0.36
    ULT
    0.36
    Activations Density 13.820%

    No Known Activations