© 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. 12687
    Prev
    Next
    INDEX
    Explanations

    articles or prepositions preceding or following certain keywords

    oai_token-act-pair · gemini-2.0-flash

    in

    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
    IsMutable
    -0.55
     MotionEvent
    -0.47
     ModelExpression
    -0.46
     represented
    -0.41
    mtable
    -0.41
    InputStream
    -0.40
    ệt
    -0.40
    FZ
    -0.39
    findpost
    -0.39
    DialogTitle
    -0.39
    POSITIVE LOGITS
     otomatig
    0.85
    Personendaten
    0.66
    antity
    0.66
    cifix
    0.62
     nahilalakip
    0.62
    UIControlState
    0.60
    цезда
    0.58
    quité
    0.58
    IContainer
    0.57
    timation
    0.57
    Activations Density 1.333%

    No Known Activations