© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6757
    Prev
    Next
    INDEX
    Explanations

    parts of the code related to managing sets of data, especially ones using lower case strings

    oai_token-act-pair · gemini-2.0-flash

    code structure terms or patterns

    np_token-act-pair-logits · gpt-4o-mini

    toLowerCase code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ()
    -1.30
    (),
    -1.19
    (
    -1.17
    ();
    -1.08
     ()
    -1.05
    ())
    -1.05
    ():
    -1.05
    ().
    -1.04
    ('
    -1.02
    (&
    -1.01
    POSITIVE LOGITS
     !_
    0.59
    tagext
    0.56
    TagMode
    0.55
    EndGlobalSection
    0.53
    unknownFields
    0.52
    ]--;
    0.52
    =[[
    0.52
    ]++;
    0.50
    Хьажоргаш
    0.49
    istoitu
    0.48
    Activations Density 0.581%

    No Known Activations