© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 1900
    Prev
    Next
    INDEX
    Explanations

    places, people, and titles related to geography, history, and royalty.

    oai_token-act-pair · gemini-2.0-flash

    place names and history

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    UnusedPrivate
    -0.52
    RenderAtEndOf
    -0.50
    ANTLR
    -0.48
     mergeFrom
    -0.46
    sand
    -0.45
    "]);
    -0.45
    رشف
    -0.44
    المكان
    -0.44
    ])),
    -0.44
    endphp
    -0.43
    POSITIVE LOGITS
    providedIn
    0.60
    XmlAccessType
    0.56
    ApplicationTests
    0.54
     EconPapers
    0.54
     uſ
    0.54
    wold
    0.52
     quæ
    0.52
     reaſon
    0.52
    ALLAS
    0.52
     purpoſe
    0.51
    Activations Density 0.394%

    No Known Activations