© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 6238
    Prev
    Next
    INDEX
    Explanations

    words or phrases used in scientific or technical writing

    oai_token-act-pair · gemini-2.0-flash

    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_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
    AndEndTag
    -0.73
    featureID
    -0.72
     kasarigan
    -0.69
     BoxDecoration
    -0.69
     AssemblyTitle
    -0.68
    ConstraintMaker
    -0.66
    TagMode
    -0.64
    RenderAtEndOf
    -0.64
    adaptiveStyles
    -0.62
     يتيمه
    -0.62
    POSITIVE LOGITS
     aperto
    0.51
     pulito
    0.49
     olivat
    0.48
     ollut
    0.47
    änä
    0.47
    owania
    0.47
     distinción
    0.47
     mourir
    0.47
     ouverte
    0.47
     版
    0.46
    Activations Density 2.196%

    No Known Activations