© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10117
    Prev
    Next
    INDEX
    Explanations

    words related to agreements and consent, as well as the action of purchasing

    oai_token-act-pair · gemini-2.0-flash

    Legal disclaimers/terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ]")]
    -0.64
     chrétiens
    -0.63
     ElementRef
    -0.60
    NetworkInfo
    -0.57
     enlace
    -0.56
     giudi
    -0.54
     zwró
    -0.54
     peuples
    -0.53
     Gewähr
    -0.52
     enfans
    -0.52
    POSITIVE LOGITS
     approve
    0.75
     approval
    0.73
     consent
    0.73
    approve
    0.73
     permission
    0.68
    approved
    0.67
     referenties
    0.65
     Approve
    0.65
     approving
    0.63
     approves
    0.62
    Activations Density 1.232%

    No Known Activations