© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11941
    Prev
    Next
    INDEX
    Explanations

    connectors of subordinate clauses, words related to working together, and words that soften statements.

    oai_token-act-pair · gemini-2.0-flash

    challenge

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Reverso
    -0.52
    Ах
    -0.50
    colgroup
    -0.50
     jLabel
    -0.48
    LookAnd
    -0.46
     betweenstory
    -0.45
    SequentialGroup
    -0.45
    域
    -0.44
     Staaten
    -0.44
    álně
    -0.44
    POSITIVE LOGITS
     challenge
    1.48
    challenge
    1.29
     challenged
    1.23
     Challenge
    1.21
     challenges
    1.17
    Challenge
    1.16
     CHALLENGE
    1.13
     challenging
    1.11
    challenged
    1.05
     desafi
    1.05
    Activations Density 2.684%

    No Known Activations