© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 5775
    Prev
    Next
    INDEX
    Explanations

    capitalized acronyms with an optional letter following them

    oai_token-act-pair · gemini-2.0-flash

    acronyms

    np_max-act-logits · gemini-2.0-flash

    say "all caps"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    <bos>
    -0.73
    -
    -0.68
    ,
    -0.68
     
    -0.66
    .
    -0.65
     n
    -0.64
     d
    -0.63
    ti
    -0.63
     and
    -0.63
     (
    -0.62
    POSITIVE LOGITS
    RenderAtEndOf
    1.06
     tartalomajánló
    1.04
     doubtnut
    1.04
    +#+#
    0.95
     فريبيس
    0.93
     незавершена
    0.90
     itſelf
    0.89
     ―――――
    0.86
    theless
    0.85
     ་་
    0.85
    Activations Density 1.216%

    No Known Activations