© 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. 8240
    Prev
    Next
    INDEX
    Explanations

    code snippets and code-related terms.

    oai_token-act-pair · gemini-2.0-flash

    code

    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
     myſelf
    -1.01
    oredCriteria
    -0.98
     itſelf
    -0.98
     purpoſe
    -0.93
     مرئيه
    -0.93
     Reſ
    -0.92
     Monfieur
    -0.92
     ſever
    -0.90
     raiſ
    -0.88
     Houſe
    -0.88
    POSITIVE LOGITS
    <bos>
    0.57
    hold
    0.50
     
    0.49
    of
    0.49
    and
    0.48
    ()*
    0.43
    Consumed
    0.42
    --)
    0.42
    to
    0.42
    ()%
    0.42
    Activations Density 8.187%

    No Known Activations