Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14454
    Prev
    Next
    INDEX
    Explanations

    structured text representing various types of data, like code snippets, mathematical expressions, or research results

    oai_token-act-pair · gemini-2.0-flash

    code and math

    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
    }).
    -0.61
    ThemeOverlay
    -0.59
    }),
    -0.54
    }
    -0.54
    fromCharCode
    -0.53
    })
    -0.51
    });
    -0.49
    IDL
    -0.49
    unknownFields
    -0.49
    marshaller
    -0.48
    POSITIVE LOGITS
    WriteBarrier
    0.61
     Мексичка
    0.59
     propOrder
    0.58
    הערות
    0.54
     <<<<<<<<<<<<<<
    0.51
    جغرافيا
    0.51
    appartamento
    0.49
    رشف
    0.49
     henvisninger
    0.48
     XMLHttpRequest
    0.48
    Activations Density 9.377%

    No Known Activations