© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5229
    Prev
    Next
    INDEX
    Explanations

    named entities, especially associated with business, media or entertainment.

    oai_token-act-pair · gemini-2.0-flash

    social media/announcements

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     Theſe
    -0.55
    /**
    -0.53
    ADATA
    -0.51
    calaure
    -0.50
    migrationBuilder
    -0.49
     Beſ
    -0.49
     Verſ
    -0.49
    OrNil
    -0.48
     datac
    -0.48
    Zaj
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    0.56
     ویکی‌پدی
    0.55
     laikā
    0.54
    цездатний
    0.53
     oike
    0.52
    ніципалі
    0.50
    ніципа
    0.50
     مواليد
    0.50
    км
    0.48
     CURIAM
    0.48
    Activations Density 7.250%

    No Known Activations