© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10485
    Prev
    Next
    INDEX
    Explanations

    HTML italics tags

    oai_token-act-pair · gemini-2.0-flash

    </em>

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    </em>
    -1.88
    </i>
    -1.63
    <bos>
    -1.24
    </u>
    -0.94
    ();*/
    -0.90
    );*/
    -0.89
    ;*/
    -0.85
    )*/
    -0.83
    });*/
    -0.81
    </h6>
    -0.79
    POSITIVE LOGITS
    tagHelperRunner
    0.86
     resourceCulture
    0.81
    IntoConstraints
    0.78
     виправивши
    0.76
    ViewFeatures
    0.75
     مشين
    0.74
    SequentialGroup
    0.68
    GEBURTSDATUM
    0.67
    expandindo
    0.66
     Roskov
    0.66
    Activations Density 2.035%

    No Known Activations