© 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
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 6173
    Prev
    Next
    INDEX
    Explanations

    text within legal or clinical documents

    oai_token-act-pair · gemini-2.0-flash

    legal/technical documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    webElementGuid
    -0.48
    atguigu
    -0.43
    bootstrapcdn
    -0.42
    ponen
    -0.42
     numberOfRows
    -0.39
    ลง
    -0.39
    лата
    -0.38
    rücke
    -0.38
    AttributeSet
    -0.38
    alors
    -0.37
    POSITIVE LOGITS
    SharedCtor
    0.77
    Composable
    0.68
    });*/
    0.66
    ")));
    
    0.65
     Mahomet
    0.65
    verwijspagina
    0.63
    Abitanti
    0.62
    };*/
    0.62
    __).
    0.61
    ]));
    
    0.60
    Activations Density 0.193%

    No Known Activations