© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15590
    Prev
    Next
    INDEX
    Explanations

    first person pronouns, auxiliary and modal verbs along with related conjunctions to find suggestions with caveats

    oai_token-act-pair · gemini-2.0-flash

    technical terms in programming or software development

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

    I

    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
    Negative Logits
    ínia
    -0.50
    ibase
    -0.46
     dasarnya
    -0.45
    achau
    -0.43
    addPreferredGap
    -0.43
    יה
    -0.43
    AutoSize
    -0.43
    ψ
    -0.43
    didSet
    -0.43
    Aim
    -0.42
    POSITIVE LOGITS
    клопе
    0.65
     contextLoads
    0.62
    sizeCache
    0.61
     насељу
    0.58
    elernt
    0.58
     BoxDecoration
    0.57
    DebuggerNonUser
    0.55
     InputDecoration
    0.54
     insuffisamment
    0.53
    ontaneous
    0.51
    Activations Density 0.644%

    No Known Activations