© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2232
    Prev
    Next
    INDEX
    Explanations

    URLs from Kickstarter

    oai_token-act-pair · gemini-2.0-flash

    kick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    XmlAccessorType
    -0.70
     estekak
    -0.67
    archiviato
    -0.66
    Referencer
    -0.65
    دام
    -0.65
    elemField
    -0.63
    AlterField
    -0.62
     Administrativna
    -0.61
    istoitu
    -0.61
     onCreateView
    -0.60
    POSITIVE LOGITS
     Kickstarter
    0.54
    TextFormField
    0.48
     "";
    0.48
    uurs
    0.47
     '',
    0.47
     alignItems
    0.47
     integral
    0.45
     TextFormField
    0.44
     Lode
    0.44
     Integral
    0.44
    Activations Density 0.712%

    No Known Activations