© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10488
    Prev
    Next
    INDEX
    Explanations

    the word "whole" or hyphenated phrases including "whole"

    oai_token-act-pair · gemini-2.0-flash

    whole

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     myſelf
    -0.93
     Efq
    -0.93
    AndEndTag
    -0.91
     raiſ
    -0.91
    IndentedString
    -0.90
     ModelExpression
    -0.90
     חיצוניים
    -0.89
    клопе
    -0.88
     betweenstory
    -0.87
     iſt
    -0.85
    POSITIVE LOGITS
     N
    0.49
     lot
    0.48
     en
    0.48
     ball
    0.42
     n
    0.42
     entender
    0.42
     owe
    0.41
    GetType
    0.40
    iente
    0.40
     on
    0.39
    Activations Density 0.338%

    No Known Activations