© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6619
    Prev
    Next
    INDEX
    Explanations

    geographical and governmental divisions or locations, especially those which have the words "North," "South," "Central," "East," or "West" in them

    oai_token-act-pair · gemini-2.0-flash

    Frisian and Carroll locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    ReusableCell
    -0.70
    >`;
    -0.65
    }";
    -0.61
    <bos>
    -0.61
    ]";
    -0.59
    ]));
    -0.57
    )";
    -0.56
    ')));
    -0.56
    ))));
    -0.55
     Conservancy
    -0.55
    POSITIVE LOGITS
    InputBorder
    0.69
    Lähteet
    0.64
    CORRECT
    0.63
     AssemblyCulture
    0.59
    arxiv
    0.59
     виправивши
    0.58
    AutoScale
    0.57
    ̍t
    0.56
    ganu
    0.56
    SPATH
    0.55
    Activations Density 1.012%

    No Known Activations