© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15017
    Prev
    Next
    INDEX
    Explanations

    a multitude of seemingly unrelated terms

    oai_token-act-pair · gemini-2.0-flash

    Newspaper articles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     ساز
    -0.48
    jamientos
    -0.47
     дописавши
    -0.46
     Right
    -0.46
    meida
    -0.45
    ​=
    -0.45
    lösung
    -0.44
    Intercept
    -0.43
    substack
    -0.42
    orrho
    -0.41
    POSITIVE LOGITS
     Organizer
    0.61
    DispatchToProps
    0.60
    PrototypeOf
    0.60
     supérieurs
    0.57
     Linger
    0.57
     newOwner
    0.57
    aarrggbb
    0.56
     NSCoder
    0.55
    UnitTesting
    0.54
     étrangères
    0.54
    Activations Density 3.492%

    No Known Activations