© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8291
    Prev
    Next
    INDEX
    Explanations

    text from scientific papers, in particular section headers and paper metadata

    oai_token-act-pair · gemini-2.0-flash

    Detects document introductions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    évaluateur
    -0.85
    orsese
    -0.54
    Viitteet
    -0.54
     Walkover
    -0.52
    ValueStyle
    -0.50
    wikimedia
    -0.48
    __':
    -0.48
     BrowserModule
    -0.47
    Composable
    -0.47
     createState
    -0.47
    POSITIVE LOGITS
    CompleteListener
    0.57
     MainAxisSize
    0.57
    glGen
    0.53
    }$​
    0.52
    glBindTexture
    0.52
    tively
    0.52
    glBindBuffer
    0.51
    CloseOperation
    0.51
    تماد
    0.50
    holung
    0.49
    Activations Density 0.675%

    No Known Activations