© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1988
    Prev
    Next
    INDEX
    Explanations

    words related to the function of electric motors

    oai_token-act-pair · gemini-2.0-flash

    technical terms and foreign language characters

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

    electrical motors

    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
    Not in Any Lists

    No Comments

    Negative Logits
    marginHorizontal
    -0.53
     Thessal
    -0.51
    enterOuterAlt
    -0.51
     pikachu
    -0.50
     Lazio
    -0.47
     Técnico
    -0.47
     Serviço
    -0.46
    omia
    -0.44
     spaniel
    -0.44
    Commodity
    -0.44
    POSITIVE LOGITS
    InSection
    0.60
    الإنجليزية
    0.60
    CodedInputStream
    0.59
    FormTagHelper
    0.57
    Portale
    0.56
    GEBURTSDATUM
    0.56
    例文帳に追加
    0.55
     通販
    0.53
     الرياضيه
    0.53
     ErrIntOverflow
    0.53
    Activations Density 1.654%

    No Known Activations