© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3539
    Prev
    Next
    INDEX
    Explanations

    list-related keywords, such as "list," "promises," and "push" along with code syntax like ".". and "]"

    oai_token-act-pair · gemini-2.0-flash

    punctuation marks and list manipulation

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

    punctuation

    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
    SerializedSize
    -0.56
    .
    -0.54
    Manbalar
    -0.48
     n
    -0.46
    ,”
    -0.46
     e
    -0.45
     ControllerBase
    -0.44
     calda
    -0.44
    .-
    -0.44
     porté
    -0.43
    POSITIVE LOGITS
     Anfitrión
    0.68
    ſelves
    0.65
     ſtate
    0.65
     Monfieur
    0.65
     raiſ
    0.65
     stiefel
    0.65
     bershka
    0.64
     &___
    0.64
    ſelf
    0.63
     whoſe
    0.63
    Activations Density 0.427%

    No Known Activations