© 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. 4424
    Prev
    Next
    INDEX
    Explanations

    code related to Java objects and Lists

    oai_token-act-pair · gemini-2.0-flash

    Programming punctuation

    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
    PreferredItem
    -1.06
    Personendaten
    -0.85
    WriteBarrier
    -0.78
    "])
    
    -0.77
    MigrationBuilder
    -0.77
     Roskov
    -0.77
    )");
    -0.77
    ")]
    
    -0.76
    TestingModule
    -0.76
    AddTagHelper
    -0.76
    POSITIVE LOGITS
    }
    0.66
    }.
    0.57
    .'
    0.52
    .»
    0.51
    }>
    0.50
    ."
    0.49
    »
    0.49
    ]
    0.48
    \}
    0.47
    InputBorder
    0.47
    Activations Density 7.691%

    No Known Activations