© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 5202
    Prev
    Next
    INDEX
    Explanations

    CSS code formatting

    oai_token-act-pair · gemini-2.0-flash

    HTML/CSS code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    PreferredItem
    -0.68
    IBOutlet
    -0.61
     Shakspeare
    -0.60
    routeProvider
    -0.59
    withIdentifier
    -0.57
    \{\\
    -0.57
    abetta
    -0.55
     Karn
    -0.54
    WriteTagHelper
    -0.54
     createState
    -0.54
    POSITIVE LOGITS
    )((
    0.48
    preso
    0.46
    )(((
    0.45
     }))
    0.45
    ChildScrollView
    0.45
     gynhyrchwyd
    0.45
     naturais
    0.42
     stage
    0.42
    rivit
    0.42
     styr
    0.42
    Activations Density 3.359%

    No Known Activations