© 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. 8498
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers

    oai_token-act-pair · gemini-2.0-flash

    tokens beginning with 'x' or containing 'x'

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

    x

    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
    parsedMessage
    -1.43
    expandindo
    -1.18
     unknownFields
    -1.15
     Paglinawan
    -1.15
     Efq
    -1.11
    principalColumn
    -1.10
     houſe
    -1.09
     Jefus
    -1.07
    InjectAttribute
    -1.07
     ſch
    -1.06
    POSITIVE LOGITS
     a
    0.65
    G
    0.59
    1
    0.58
      
    0.56
     G
    0.54
     po
    0.53
    .
    0.53
    vi
    0.51
    </strong>
    0.50
     M
    0.50
    Activations Density 0.773%

    No Known Activations