© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4224
    Prev
    Next
    INDEX
    Explanations

    instances of the prefix "ab"

    oai_token-act-pair · gemini-2.0-flash

    ab

    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
    WireFormatLite
    -0.60
    arXiv
    -0.56
    rungsseite
    -0.55
    kmale
    -0.53
     lose
    -0.52
     lost
    -0.52
    okhttp
    -0.51
    돼
    -0.51
    mtable
    -0.51
    lidene
    -0.47
    POSITIVE LOGITS
     itſelf
    0.62
    ՚
    0.60
    ſelves
    0.60
    IndentedString
    0.56
     Majefty
    0.54
    WebVitals
    0.53
     whiteColor
    0.52
     absurdo
    0.52
     חיצוניים
    0.51
     Solidar
    0.51
    Activations Density 0.367%

    No Known Activations