© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 1271
    Prev
    Next
    INDEX
    Explanations

    code or markup, particularly related to HTML, CSS, Javascript, and data encoding

    oai_token-act-pair · gemini-2.0-flash

    say quote

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    </blockquote>
    -0.96
    >";
    -0.90
    ;}
    -0.88
    AndEndTag
    -0.87
     };
    -0.86
    }";
    -0.85
    </h4>
    -0.84
     };
    -0.84
    ;";
    -0.83
    >';
    -0.81
    POSITIVE LOGITS
    ").
    0.90
    ')
    0.87
    '):
    0.85
    ').
    0.82
    "),
    0.82
    ")
    0.81
    '),
    0.79
    "):
    0.77
    ")==
    0.68
    ")
    0.65
    Activations Density 5.141%

    No Known Activations