© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4481
    Prev
    Next
    INDEX
    Explanations

    legal and business contract language as well as quantity of items

    oai_token-act-pair · gemini-2.0-flash

    off

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    الإنجليزية
    -0.52
    kháu
    -0.50
    LookAnd
    -0.48
     MainAxisSize
    -0.44
    batik
    -0.40
     chi̍t
    -0.40
     cherchés
    -0.39
     pitié
    -0.39
    espn
    -0.38
    IsContent
    -0.38
    POSITIVE LOGITS
     off
    1.94
     Off
    1.47
    off
    1.34
    Off
    1.30
     OFF
    1.27
    OFF
    1.07
    オフ
    0.96
     offs
    0.93
    offs
    0.91
     オフ
    0.89
    Activations Density 2.001%

    No Known Activations