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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10212
    Prev
    Next
    INDEX
    Explanations

    language related to schools, teachers and employees, especially in regards to job descriptions and recognition

    oai_token-act-pair · gemini-2.0-flash

    Employees and personnel

    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
     ModelExpression
    -0.81
     """
    -0.70
    %");
    -0.69
     Verw
    -0.68
    numerusform
    -0.68
     invokingState
    -0.63
    )";
    -0.63
    ]));
    -0.62
    }$​
    -0.61
    WireFormat
    -0.60
    POSITIVE LOGITS
    ersen
    0.45
    MLLoader
    0.44
    addCriterion
    0.44
     Dauer
    0.44
     Sal
    0.43
     ranked
    0.41
    群
    0.41
     full
    0.41
    言って
    0.40
     پرد
    0.39
    Activations Density 1.390%

    No Known Activations