© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2959
    Prev
    Next
    INDEX
    Explanations

    the word "most" or related words and numbers, especially as it describes ranking in medical or research contexts.

    oai_token-act-pair · gemini-2.0-flash

    common

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     linkovi
    -0.58
     CreateTagHelper
    -0.57
    erdings
    -0.56
     صوتيه
    -0.56
     transfieras
    -0.56
    WireFormatLite
    -0.55
    ⓘ
    -0.54
     noDo
    -0.54
    enumi
    -0.53
    存于互联网档案馆
    -0.52
    POSITIVE LOGITS
     common
    2.33
    common
    2.13
    Common
    1.95
     Common
    1.91
     COMMON
    1.76
    COMMON
    1.76
     commonest
    1.71
     commonly
    1.59
     comunes
    1.55
     popular
    1.55
    Activations Density 1.977%

    No Known Activations