© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14350
    Prev
    Next
    INDEX
    Explanations

    snippets of code, math forumulae, and quoted speech, possibly prioritizing negative connotations

    oai_token-act-pair · gemini-2.0-flash

    Quotation marks/parentheses

    np_max-act-logits · gemini-2.0-flash

    opening punctuation

    np_max-act-logits · gpt-5-mini
    Triggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æus
    -1.11
    ineſs
    -1.09
    ratulations
    -1.09
    BibitemShut
    -1.05
    iffance
    -1.05
    hematical
    -1.03
    iſter
    -1.01
     nahilalakip
    -1.01
    bibfield
    -1.01
    ſſer
    -1.01
    POSITIVE LOGITS
    to
    0.64
    in
    0.63
    I
    0.63
    p
    0.63
    P
    0.62
    de
    0.62
    M
    0.62
    b
    0.61
    v
    0.60
    V
    0.60
    Activations Density 23.442%

    No Known Activations