© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6780
    Prev
    Next
    INDEX
    Explanations

    references to canons in judicial or legal settings

    oai_token-act-pair · gemini-2.0-flash

    ons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     hope
    -0.48
    ويد
    -0.44
    olymer
    -0.43
     卓
    -0.43
     hoped
    -0.43
     new
    -0.42
    謂
    -0.40
    揮
    -0.40
     snap
    -0.40
    יתה
    -0.40
    POSITIVE LOGITS
     channel
    1.16
     Channel
    1.14
     Channels
    1.09
     CHANNEL
    1.07
     channels
    1.06
    channel
    1.06
    Channel
    1.02
     canales
    0.98
    CHANNEL
    0.98
     canale
    0.98
    Activations Density 0.361%

    No Known Activations