© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2730
    Prev
    Next
    INDEX
    Explanations

    descriptions of power saws

    oai_token-act-pair · gemini-2.0-flash

    with. Method #1, failed the other methods

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    orianCalendar
    -0.63
     SAL
    -0.46
     Jal
    -0.45
    gcm
    -0.45
    bcrypt
    -0.44
    SAL
    -0.44
    Schedulers
    -0.44
    AGU
    -0.44
     Jär
    -0.43
    ButtonItem
    -0.42
    POSITIVE LOGITS
    OGND
    0.85
    تقاوى
    0.78
    tagHelperRunner
    0.72
    SharedCtor
    0.65
    MigrationBuilder
    0.64
    Personensuche
    0.63
     للاسماء
    0.62
    ///</
    0.60
     Мексичка
    0.60
     noqa
    0.60
    Activations Density 1.800%

    No Known Activations