© 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. 11389
    Prev
    Next
    INDEX
    Explanations

    Japanese text

    oai_token-act-pair · gemini-2.0-flash

    Non-English languages/code

    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
     ་་
    -0.84
     itſelf
    -0.83
     ſind
    -0.82
     surla
    -0.79
     tfsi
    -0.77
    OGND
    -0.75
     Wicidata
    -0.74
    RenderAtEndOf
    -0.73
     مرئيه
    -0.73
     iſt
    -0.73
    POSITIVE LOGITS
     bajas
    0.39
     kandang
    0.35
     confianza
    0.35
     копия
    0.35
     néz
    0.35
    azan
    0.35
     trasparente
    0.34
     parlé
    0.34
     garantías
    0.34
    okan
    0.34
    Activations Density 1.733%

    No Known Activations