Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 14645
    Prev
    Next
    INDEX
    Explanations

    descriptions of the engineering and mechanics of valves and engines

    oai_token-act-pair · gemini-2.0-flash

    valve

    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
    Lähteet
    -0.66
    ########.
    -0.60
    ävän
    -0.56
     ivelany
    -0.55
    ValueGenerated
    -0.55
    Хьажоргаш
    -0.55
    aranja
    -0.55
     Rys
    -0.54
    PerformLayout
    -0.53
    ="@+
    -0.53
    POSITIVE LOGITS
    ClientSize
    0.53
    hObject
    0.52
    ])->
    0.52
    DeleteCommand
    0.49
    ictwa
    0.49
     Felsen
    0.48
    ItemBackground
    0.48
     lif
    0.47
     spool
    0.46
     Erich
    0.46
    Activations Density 1.474%

    No Known Activations