© 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. 4348
    Prev
    Next
    INDEX
    Explanations

    text related to washing machine settings and features

    oai_token-act-pair · gemini-2.0-flash

    washing machines

    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
    verwijspagina
    -0.58
     beginnetje
    -0.56
    Enter
    -0.54
    SequentialGroup
    -0.54
     ataca
    -0.52
     verwijzen
    -0.52
     Anfitrión
    -0.51
     ENTER
    -0.51
     unu
    -0.51
    av
    -0.50
    POSITIVE LOGITS
    djangoproject
    0.56
    GenerationType
    0.54
    issy
    0.50
     machine
    0.49
    ducers
    0.48
     חיצוניים
    0.48
    ]")]
    0.48
    adaptiveStyles
    0.46
    Controllo
    0.45
    ParallelGroup
    0.45
    Activations Density 0.694%

    No Known Activations