© 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. 2-GEMMASCOPE-TRANSCODER-16K
    4. 10508
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to have a wide variety of triggers, from code-related terms to legal and conversational phrases, indicating a possible focus on structured or argumentative text across different domains.

    oai_token-act-pair · gemini-2.0-flash

    steps

    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
    Obrázky
    -0.73
    ]")]
    -0.73
    })));
    -0.69
     通販
    -0.68
    }))
    
    -0.66
    \"");
    -0.66
    "},
    
    -0.65
    ])));
    -0.65
     hilux
    -0.65
    ']))
    
    -0.65
    POSITIVE LOGITS
    <bos>
    0.85
     
    0.48
     sta
    0.43
    GEBURTSDATUM
    0.42
    QtWidgets
    0.42
     NUKAT
    0.42
    onAttach
    0.41
    Demografie
    0.40
    ERMIN
    0.40
    是一
    0.40
    Activations Density 14.872%

    No Known Activations