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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 993
    Prev
    Next
    INDEX
    Explanations

    Java code including package names

    oai_token-act-pair · gemini-2.0-flash

    Code and programming text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    AccessorTable
    -0.79
     Roskov
    -0.69
    )$}
    -0.69
    })$}
    -0.69
    ]")]
    -0.68
    RegistryLite
    -0.68
     disambiguazione
    -0.67
     }}$}
    -0.65
    MarshalTo
    -0.64
    parsedMessage
    -0.63
    POSITIVE LOGITS
    Println
    0.50
    user
    0.49
    Biography
    0.47
    NORE
    0.44
    function
    0.44
    method
    0.42
    cost
    0.42
    com
    0.42
    urn
    0.42
    шой
    0.42
    Activations Density 0.323%

    No Known Activations