© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13219
    Prev
    Next
    INDEX
    Explanations

    words related to toilets and flushing

    oai_token-act-pair · gemini-2.0-flash

    words related to toilets and bathroom contexts

    np_token-act-pair-logits · gpt-4o-mini

    toilet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     kuni
    -0.45
    プーン
    -0.42
    Packard
    -0.42
     systemic
    -0.41
     kuti
    -0.41
    قایناقلار
    -0.41
    リーブ
    -0.40
     photon
    -0.39
     Hiz
    -0.39
    lepší
    -0.38
    POSITIVE LOGITS
    kloped
    0.76
    CodedInputStream
    0.75
    Xna
    0.71
    IMPORTED
    0.67
    RRect
    0.66
     Aufs
    0.65
     viewDidLoad
    0.64
    Portale
    0.63
     mouseY
    0.61
    NameInMap
    0.60
    Activations Density 1.140%

    No Known Activations