© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12160
    Prev
    Next
    INDEX
    Explanations

    substrings of hexadecimal-like sequences, especially those used as IDs.

    oai_token-act-pair · gemini-2.0-flash

    code with hex values

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    </strong>
    -0.65
     the
    -0.57
    ↵
    -0.55
    ’
    -0.54
    </em>
    -0.54
      
    -0.54
     No
    -0.54
    '
    -0.52
     
    -0.52
     Trä
    -0.51
    POSITIVE LOGITS
    parsedMessage
    1.48
     EClass
    1.35
    featureID
    1.34
    +#+#
    1.34
    DockStyle
    1.34
    MigrationBuilder
    1.33
     مشين
    1.31
     '\\;'
    1.30
    ValueStyle
    1.29
     ModelExpression
    1.26
    Activations Density 1.548%

    No Known Activations