© 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. 8544
    Prev
    Next
    INDEX
    Explanations

    code and code-adjacent tokens, particularly relating to compilation and import

    oai_token-act-pair · gemini-2.0-flash

    programming syntax and structures

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

    Code Snippets

    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
    )");
    -0.75
    ")]
    -0.71
     يتيمه
    -0.71
    =?";
    -0.71
    "):
    -0.70
    )]
    -0.70
    >--}}
    -0.68
    )";
    -0.66
    )"),
    -0.66
    '))
    -0.65
    POSITIVE LOGITS
     EdgeInsets
    0.71
    </>
    0.63
    /,
    0.59
    -.
    0.58
    /.
    0.57
    -,
    0.55
    MENAFN
    0.52
    /}{
    0.52
     BoxDecoration
    0.51
    XmlAccessType
    0.51
    Activations Density 9.760%

    No Known Activations