© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6862
    Prev
    Next
    INDEX
    Explanations

    prepositions, conjunctions, and articles in the context of fighting championships

    oai_token-act-pair · gemini-2.0-flash

    code and foreign languages

    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
    ografija
    -0.61
    __":
    -0.61
    providedIn
    -0.58
    webElementGuid
    -0.57
    +:+
    -0.56
     seaborn
    -0.56
     disambiguazione
    -0.54
    DOCTYPE
    -0.51
    }(),
    -0.49
    AndroidJUnit
    -0.48
    POSITIVE LOGITS
    Datuak
    0.62
     nakalista
    0.60
    kuuta
    0.58
     ویکی‌پدیا
    0.51
     Kond
    0.51
    Ӕ
    0.49
    WriteTagHelper
    0.49
     betweenstory
    0.47
    ruptedException
    0.46
     Penna
    0.46
    Activations Density 0.277%

    No Known Activations