© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 2294
    Prev
    Next
    INDEX
    Explanations

    source code with escape sequences and string concatenation

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    AndEndTag
    -0.83
     estekak
    -0.71
     "..\..\
    -0.69
     gyhoeddwyd
    -0.69
    exitRule
    -0.68
     defaultstate
    -0.66
    adpleegd
    -0.66
     CreateTagHelper
    -0.64
    ]--;
    -0.64
     "..\..\..\
    -0.63
    POSITIVE LOGITS
    usercontent
    0.59
     nacionales
    0.48
     ‘
    0.47
    <bos>
    0.46
    Re
    0.45
     „
    0.45
    аза
    0.43
    copus
    0.43
     '
    0.43
     rych
    0.42
    Activations Density 10.218%

    No Known Activations