© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10317
    Prev
    Next
    INDEX
    Explanations

    words implying a connection to the reader or writer, such as personal pronouns, compliments, and related verbs

    oai_token-act-pair · gemini-2.0-flash

    yours

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    :✨
    -0.71
     Ak
    -0.60
    Ak
    -0.57
     yours
    -0.54
    Yours
    -0.50
    oro
    -0.50
    yle
    -0.50
     vekt
    -0.49
    cel
    -0.48
     homework
    -0.47
    POSITIVE LOGITS
    adpleegd
    0.86
    ImageContext
    0.77
    sizeCache
    0.74
    الحياه
    0.72
    aarrggbb
    0.71
    
    0.65
     الاطلاع
    0.64
     heapq
    0.64
    tagHelperRunner
    0.63
    LookAnd
    0.63
    Activations Density 9.843%

    No Known Activations