© 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. 5895
    Prev
    Next
    INDEX
    Explanations

    the prefix "en"

    oai_token-act-pair · gemini-2.0-flash

    En

    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
    mozilla
    -0.56
    yorsunuz
    -0.56
    pett
    -0.54
    stdio
    -0.50
    ischem
    -0.50
    moveToFirst
    -0.49
    secutive
    -0.49
    mber
    -0.48
    arkan
    -0.48
     Ferr
    -0.48
    POSITIVE LOGITS
    Jereo
    0.62
    Personendaten
    0.58
     OFDb
    0.58
    tagHelperRunner
    0.57
    Jîn
    0.56
     createContext
    0.56
    SourceChecksum
    0.56
    bewerken
    0.54
    webElementXpaths
    0.52
    numerusform
    0.52
    Activations Density 0.272%

    No Known Activations