© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1574
    Prev
    Next
    INDEX
    Explanations

    code or mathematical formulas

    oai_token-act-pair · gemini-2.0-flash

    Code syntax

    np_max-act · gemini-2.0-flash

    braces and parentheses

    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_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
    :
    -0.50
    do
    -0.45
     three
    -0.44
    ids
    -0.43
     tham
    -0.42
    '
    -0.40
    лита
    -0.40
    ساب
    -0.40
    id
    -0.39
    Flo
    -0.38
    POSITIVE LOGITS
     CreateTagHelper
    1.26
    WebVitals
    1.18
     snippetHide
    1.06
    ensement
    1.05
     AssemblyCulture
    1.02
    PreferredItem
    0.97
    aarrggbb
    0.95
    ########.
    0.94
     lenker
    0.94
    AndEndTag
    0.94
    Activations Density 5.426%

    No Known Activations