© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 12418
    Prev
    Next
    INDEX
    Explanations

    words relating to formal, written agreements

    oai_token-act-pair · gemini-2.0-flash

    contract/agreement

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
     turno
    -0.45
     ustedes
    -0.43
     contrato
    -0.41
     vastaan
    -0.40
     convenio
    -0.40
     BrowserModule
    -0.39
     en
    -0.37
     sahiptir
    -0.37
    show
    -0.36
    ])))
    -0.36
    POSITIVE LOGITS
     AssemblyCompany
    0.71
     kasarigan
    0.68
     CreateTagHelper
    0.67
     Ouverture
    0.66
     correctes
    0.65
    WithMany
    0.64
    AnchorTagHelper
    0.64
    izowane
    0.63
     تانيه
    0.63
    uxxxx
    0.62
    Activations Density 6.008%

    No Known Activations