© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 13766
    Prev
    Next
    INDEX
    Explanations

    a mix of corporate-speak, legalese, and health-related vocabulary

    oai_token-act-pair · gemini-2.0-flash

    shareholders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    脚注の使い方
    -1.01
    featureID
    -0.71
    breo
    -0.65
    PMailer
    -0.63
    StructEnd
    -0.63
    #+#
    -0.62
    Manbalar
    -0.60
     برانيه
    -0.60
    Rüyada
    -0.59
    الإنجليزية
    -0.57
    POSITIVE LOGITS
    .*")]
    0.52
    bigr
    0.50
     تانيه
    0.49
    haviors
    0.48
    openConnection
    0.45
    #
    0.44
    hdashline
    0.44
     gevo
    0.44
     مما
    0.43
    ↵↵
    0.43
    Activations Density 0.112%

    No Known Activations