© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9585
    Prev
    Next
    INDEX
    Explanations

    the words "myself", forms of "I am", forms of "you have", and the word "lately"

    oai_token-act-pair · gemini-2.0-flash

    personal perspective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    de
    -0.54
    var
    -0.51
     discrimin
    -0.49
    Layer
    -0.48
    ant
    -0.48
    layer
    -0.48
    ma
    -0.48
    delta
    -0.48
     schwe
    -0.47
    anti
    -0.45
    POSITIVE LOGITS
    :✨
    0.92
     Мексичка
    0.89
    initely
    0.85
     ModelExpression
    0.85
    etheless
    0.84
    cerely
    0.82
    Personensuche
    0.82
     незавершена
    0.82
    thâu
    0.81
    تقاوى
    0.81
    Activations Density 0.428%

    No Known Activations