© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12955
    Prev
    Next
    INDEX
    Explanations

    hyphens and other formatting characters as well as salutations like "thanks" and website URLs

    oai_token-act-pair · gemini-2.0-flash

    dashes/ellipses/tildes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    DockStyle
    -0.78
     الحره
    -0.73
     estekak
    -0.66
    ngrx
    -0.65
     "..\..\
    -0.60
    ])):
    -0.60
    aksikan
    -0.58
    parsedMessage
    -0.58
    RotationOrder
    -0.57
    Хьажоргаш
    -0.57
    POSITIVE LOGITS
    Rhestr
    0.44
     समीक्षाएं
    0.40
     IBOutlet
    0.40
    GraphicsUnit
    0.40
    toISOString
    0.37
     Businesses
    0.37
     internazionale
    0.37
     ioutil
    0.36
     acuer
    0.36
     चीज़ों
    0.36
    Activations Density 1.070%

    No Known Activations