© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 10849
    Prev
    Next
    INDEX
    Explanations

    a hodgepodge of words, possibly from a nonsensical or poorly translated text.

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    detectChanges
    -0.63
    BeginContext
    -0.56
    SizeF
    -0.50
    Geplaatst
    -0.48
    اتب
    -0.45
    AndroidJUnit
    -0.45
    Affili
    -0.45
    WebVitals
    -0.44
    garder
    -0.44
    becker
    -0.44
    POSITIVE LOGITS
     виправивши
    0.55
    reactstrap
    0.52
    abinieri
    0.52
    Autoritní
    0.50
    Diweddarwch
    0.50
    gameserver
    0.49
    isand
    0.49
     مشين
    0.49
    endphp
    0.49
    บัติ
    0.48
    Activations Density 1.405%

    No Known Activations