© 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. 7276
    Prev
    Next
    INDEX
    Explanations

    research acknowledgements and funding statements

    oai_token-act-pair · gemini-2.0-flash

    programming terms or variables

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

    Acknowledgements and Thanks

    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
    bcryptjs
    -0.61
    RepeatedField
    -0.56
    sendRedirect
    -0.56
    LookAnd
    -0.54
    Added
    -0.51
    θρώ
    -0.50
    TagMode
    -0.45
    Known
    -0.45
     acondicionado
    -0.44
    phonse
    -0.43
    POSITIVE LOGITS
     jsPsych
    0.75
     tartalomajánló
    0.69
    CPtr
    0.67
    TestingModule
    0.64
    enumi
    0.60
    tvguidetime
    0.59
     >=",
    0.59
     LoggerFactory
    0.57
     ويكيميديا
    0.54
    VERSE
    0.53
    Activations Density 3.819%

    No Known Activations