© 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. 2815
    Prev
    Next
    INDEX
    Explanations

    code snippets with certain keywords such as 'function', 'mock', 'class', 'id', 'data', and/or 'module'

    oai_token-act-pair · gemini-2.0-flash

    Punctuation and symbols

    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
     InputDecoration
    -0.62
     EconPapers
    -0.60
    hésite
    -0.56
    hésitez
    -0.53
     itſelf
    -0.53
     Theſe
    -0.52
     becauſe
    -0.52
     تانيه
    -0.51
     neceffary
    -0.51
    AutoField
    -0.51
    POSITIVE LOGITS
    ,
    1.95
    ),
    1.63
    ,
    1.63
    (),
    1.51
    !,
    1.45
    ?,
    1.45
    *,
    1.45
    ,’
    1.43
    [],
    1.43
    .,
    1.41
    Activations Density 38.018%

    No Known Activations