© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9189
    Prev
    Next
    INDEX
    Explanations

    text where someone wants or needs something to occur, often with an explanation of the process

    oai_token-act-pair · gemini-2.0-flash

    Legal orders and requests

    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
    quels
    -0.60
     cual
    -0.47
    Demografía
    -0.46
    ActionResult
    -0.44
     GenerationType
    -0.43
     ActionResult
    -0.43
    ractable
    -0.43
    OrNil
    -0.42
    ValueStyle
    -0.42
    Summar
    -0.42
    POSITIVE LOGITS
     that
    1.91
     bahwa
    1.28
     rằng
    1.20
    that
    1.16
     dass
    1.09
     że
    1.07
     että
    1.04
     bahawa
    0.97
     ότι
    0.96
     कि
    0.92
    Activations Density 0.933%

    No Known Activations